Add

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

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
+    }
+}

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

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
+    }
+}

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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