bobox's picture
Training in progress, step 3826, checkpoint
04024ed verified
raw
history blame contribute delete
No virus
50.6 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.6000627352572145,
"eval_steps": 479,
"global_step": 3826,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0075282308657465494,
"grad_norm": 87.12931823730469,
"learning_rate": 3.147218736930155e-07,
"loss": 12.3074,
"step": 48
},
{
"epoch": 0.015056461731493099,
"grad_norm": 64.15751647949219,
"learning_rate": 6.660393140945211e-07,
"loss": 15.7221,
"step": 96
},
{
"epoch": 0.02258469259723965,
"grad_norm": 81.39651489257812,
"learning_rate": 1.0173567544960265e-06,
"loss": 10.8027,
"step": 144
},
{
"epoch": 0.030112923462986198,
"grad_norm": 22.048904418945312,
"learning_rate": 1.3686741948975323e-06,
"loss": 8.9559,
"step": 192
},
{
"epoch": 0.037641154328732745,
"grad_norm": 11.542724609375,
"learning_rate": 1.7126725219573398e-06,
"loss": 8.8511,
"step": 240
},
{
"epoch": 0.0451693851944793,
"grad_norm": 10.625059127807617,
"learning_rate": 2.063989962358846e-06,
"loss": 9.3478,
"step": 288
},
{
"epoch": 0.05269761606022585,
"grad_norm": 14.21434211730957,
"learning_rate": 2.415307402760351e-06,
"loss": 8.8892,
"step": 336
},
{
"epoch": 0.060225846925972396,
"grad_norm": 13.216053009033203,
"learning_rate": 2.7666248431618565e-06,
"loss": 8.3008,
"step": 384
},
{
"epoch": 0.06775407779171895,
"grad_norm": 22.503334045410156,
"learning_rate": 3.117942283563362e-06,
"loss": 7.3455,
"step": 432
},
{
"epoch": 0.07512547051442911,
"eval_nli-pairs_loss": 6.591032028198242,
"eval_nli-pairs_runtime": 4.3469,
"eval_nli-pairs_samples_per_second": 46.01,
"eval_nli-pairs_steps_per_second": 1.15,
"eval_sts-test_pearson_cosine": 0.39488461174644296,
"eval_sts-test_pearson_dot": 0.15593446481859455,
"eval_sts-test_pearson_euclidean": 0.39975070029693277,
"eval_sts-test_pearson_manhattan": 0.4314268556737928,
"eval_sts-test_pearson_max": 0.4314268556737928,
"eval_sts-test_spearman_cosine": 0.3997824055251076,
"eval_sts-test_spearman_dot": 0.14324216739430146,
"eval_sts-test_spearman_euclidean": 0.40262274612650517,
"eval_sts-test_spearman_manhattan": 0.42925492969387746,
"eval_sts-test_spearman_max": 0.42925492969387746,
"step": 479
},
{
"epoch": 0.07512547051442911,
"eval_vitaminc-pairs_loss": 6.247874736785889,
"eval_vitaminc-pairs_runtime": 1.4382,
"eval_vitaminc-pairs_samples_per_second": 115.426,
"eval_vitaminc-pairs_steps_per_second": 2.781,
"step": 479
},
{
"epoch": 0.07512547051442911,
"eval_sts-label_loss": 3.371708869934082,
"eval_sts-label_runtime": 0.3925,
"eval_sts-label_samples_per_second": 509.603,
"eval_sts-label_steps_per_second": 12.74,
"step": 479
},
{
"epoch": 0.07512547051442911,
"eval_qnli-contrastive_loss": 3.5311310291290283,
"eval_qnli-contrastive_runtime": 0.2814,
"eval_qnli-contrastive_samples_per_second": 710.798,
"eval_qnli-contrastive_steps_per_second": 17.77,
"step": 479
},
{
"epoch": 0.07512547051442911,
"eval_scitail-pairs-qa_loss": 5.4017333984375,
"eval_scitail-pairs-qa_runtime": 1.1087,
"eval_scitail-pairs-qa_samples_per_second": 180.387,
"eval_scitail-pairs-qa_steps_per_second": 4.51,
"step": 479
},
{
"epoch": 0.07512547051442911,
"eval_scitail-pairs-pos_loss": 4.29502534866333,
"eval_scitail-pairs-pos_runtime": 2.4269,
"eval_scitail-pairs-pos_samples_per_second": 82.41,
"eval_scitail-pairs-pos_steps_per_second": 2.06,
"step": 479
},
{
"epoch": 0.07512547051442911,
"eval_xsum-pairs_loss": 3.540722370147705,
"eval_xsum-pairs_runtime": 1.0447,
"eval_xsum-pairs_samples_per_second": 191.444,
"eval_xsum-pairs_steps_per_second": 4.786,
"step": 479
},
{
"epoch": 0.07512547051442911,
"eval_compression-pairs_loss": 2.8060033321380615,
"eval_compression-pairs_runtime": 0.2399,
"eval_compression-pairs_samples_per_second": 833.621,
"eval_compression-pairs_steps_per_second": 20.841,
"step": 479
},
{
"epoch": 0.07512547051442911,
"eval_sciq_pairs_loss": 10.621454238891602,
"eval_sciq_pairs_runtime": 9.0638,
"eval_sciq_pairs_samples_per_second": 22.066,
"eval_sciq_pairs_steps_per_second": 0.552,
"step": 479
},
{
"epoch": 0.07512547051442911,
"eval_qasc_pairs_loss": 7.7197771072387695,
"eval_qasc_pairs_runtime": 1.2078,
"eval_qasc_pairs_samples_per_second": 165.595,
"eval_qasc_pairs_steps_per_second": 4.14,
"step": 479
},
{
"epoch": 0.07512547051442911,
"eval_openbookqa_pairs_loss": 7.620975494384766,
"eval_openbookqa_pairs_runtime": 1.053,
"eval_openbookqa_pairs_samples_per_second": 189.941,
"eval_openbookqa_pairs_steps_per_second": 4.749,
"step": 479
},
{
"epoch": 0.07512547051442911,
"eval_msmarco_pairs_loss": 8.353594779968262,
"eval_msmarco_pairs_runtime": 2.5338,
"eval_msmarco_pairs_samples_per_second": 78.932,
"eval_msmarco_pairs_steps_per_second": 1.973,
"step": 479
},
{
"epoch": 0.07512547051442911,
"eval_nq_pairs_loss": 7.995354652404785,
"eval_nq_pairs_runtime": 5.7107,
"eval_nq_pairs_samples_per_second": 35.022,
"eval_nq_pairs_steps_per_second": 0.876,
"step": 479
},
{
"epoch": 0.07512547051442911,
"eval_trivia_pairs_loss": 8.177907943725586,
"eval_trivia_pairs_runtime": 9.1824,
"eval_trivia_pairs_samples_per_second": 21.781,
"eval_trivia_pairs_steps_per_second": 0.545,
"step": 479
},
{
"epoch": 0.07512547051442911,
"eval_quora_pairs_loss": 1.1983369588851929,
"eval_quora_pairs_runtime": 0.659,
"eval_quora_pairs_samples_per_second": 303.48,
"eval_quora_pairs_steps_per_second": 7.587,
"step": 479
},
{
"epoch": 0.07512547051442911,
"eval_gooaq_pairs_loss": 7.4573974609375,
"eval_gooaq_pairs_runtime": 1.5917,
"eval_gooaq_pairs_samples_per_second": 125.65,
"eval_gooaq_pairs_steps_per_second": 3.141,
"step": 479
},
{
"epoch": 0.07512547051442911,
"eval_mrpc_pairs_loss": 2.1152825355529785,
"eval_mrpc_pairs_runtime": 0.241,
"eval_mrpc_pairs_samples_per_second": 829.751,
"eval_mrpc_pairs_steps_per_second": 20.744,
"step": 479
},
{
"epoch": 0.07528230865746549,
"grad_norm": 17.753456115722656,
"learning_rate": 3.469259723964868e-06,
"loss": 8.0369,
"step": 480
},
{
"epoch": 0.08281053952321205,
"grad_norm": 12.012594223022461,
"learning_rate": 3.820577164366374e-06,
"loss": 6.2732,
"step": 528
},
{
"epoch": 0.0903387703889586,
"grad_norm": 34.92698287963867,
"learning_rate": 4.1718946047678796e-06,
"loss": 7.8529,
"step": 576
},
{
"epoch": 0.09786700125470514,
"grad_norm": 23.564632415771484,
"learning_rate": 4.523212045169385e-06,
"loss": 5.8643,
"step": 624
},
{
"epoch": 0.1053952321204517,
"grad_norm": 22.126293182373047,
"learning_rate": 4.874529485570891e-06,
"loss": 6.3179,
"step": 672
},
{
"epoch": 0.11292346298619825,
"grad_norm": 25.067686080932617,
"learning_rate": 5.225846925972396e-06,
"loss": 6.1175,
"step": 720
},
{
"epoch": 0.12045169385194479,
"grad_norm": 29.170730590820312,
"learning_rate": 5.577164366373902e-06,
"loss": 5.2392,
"step": 768
},
{
"epoch": 0.12797992471769135,
"grad_norm": 29.377540588378906,
"learning_rate": 5.928481806775407e-06,
"loss": 5.8324,
"step": 816
},
{
"epoch": 0.1355081555834379,
"grad_norm": 33.512088775634766,
"learning_rate": 6.279799247176913e-06,
"loss": 5.1523,
"step": 864
},
{
"epoch": 0.14303638644918445,
"grad_norm": 32.54931640625,
"learning_rate": 6.6311166875784185e-06,
"loss": 6.0303,
"step": 912
},
{
"epoch": 0.15025094102885822,
"eval_nli-pairs_loss": 4.317643165588379,
"eval_nli-pairs_runtime": 4.0158,
"eval_nli-pairs_samples_per_second": 49.803,
"eval_nli-pairs_steps_per_second": 1.245,
"eval_sts-test_pearson_cosine": 0.6751726661173544,
"eval_sts-test_pearson_dot": 0.5308173325280101,
"eval_sts-test_pearson_euclidean": 0.6660519042507951,
"eval_sts-test_pearson_manhattan": 0.6723411683739887,
"eval_sts-test_pearson_max": 0.6751726661173544,
"eval_sts-test_spearman_cosine": 0.6458966208807124,
"eval_sts-test_spearman_dot": 0.5040208096497271,
"eval_sts-test_spearman_euclidean": 0.6447205374312966,
"eval_sts-test_spearman_manhattan": 0.6498560301461127,
"eval_sts-test_spearman_max": 0.6498560301461127,
"step": 958
},
{
"epoch": 0.15025094102885822,
"eval_vitaminc-pairs_loss": 6.306981563568115,
"eval_vitaminc-pairs_runtime": 1.4737,
"eval_vitaminc-pairs_samples_per_second": 112.643,
"eval_vitaminc-pairs_steps_per_second": 2.714,
"step": 958
},
{
"epoch": 0.15025094102885822,
"eval_sts-label_loss": 3.7677345275878906,
"eval_sts-label_runtime": 0.4136,
"eval_sts-label_samples_per_second": 483.59,
"eval_sts-label_steps_per_second": 12.09,
"step": 958
},
{
"epoch": 0.15025094102885822,
"eval_qnli-contrastive_loss": 2.8633975982666016,
"eval_qnli-contrastive_runtime": 0.2816,
"eval_qnli-contrastive_samples_per_second": 710.123,
"eval_qnli-contrastive_steps_per_second": 17.753,
"step": 958
},
{
"epoch": 0.15025094102885822,
"eval_scitail-pairs-qa_loss": 1.4301409721374512,
"eval_scitail-pairs-qa_runtime": 1.0526,
"eval_scitail-pairs-qa_samples_per_second": 190.003,
"eval_scitail-pairs-qa_steps_per_second": 4.75,
"step": 958
},
{
"epoch": 0.15025094102885822,
"eval_scitail-pairs-pos_loss": 2.468087673187256,
"eval_scitail-pairs-pos_runtime": 2.3275,
"eval_scitail-pairs-pos_samples_per_second": 85.928,
"eval_scitail-pairs-pos_steps_per_second": 2.148,
"step": 958
},
{
"epoch": 0.15025094102885822,
"eval_xsum-pairs_loss": 2.153658151626587,
"eval_xsum-pairs_runtime": 1.0409,
"eval_xsum-pairs_samples_per_second": 192.151,
"eval_xsum-pairs_steps_per_second": 4.804,
"step": 958
},
{
"epoch": 0.15025094102885822,
"eval_compression-pairs_loss": 1.6288033723831177,
"eval_compression-pairs_runtime": 0.2383,
"eval_compression-pairs_samples_per_second": 839.253,
"eval_compression-pairs_steps_per_second": 20.981,
"step": 958
},
{
"epoch": 0.15025094102885822,
"eval_sciq_pairs_loss": 9.78779411315918,
"eval_sciq_pairs_runtime": 9.0233,
"eval_sciq_pairs_samples_per_second": 22.165,
"eval_sciq_pairs_steps_per_second": 0.554,
"step": 958
},
{
"epoch": 0.15025094102885822,
"eval_qasc_pairs_loss": 3.7814972400665283,
"eval_qasc_pairs_runtime": 1.2108,
"eval_qasc_pairs_samples_per_second": 165.179,
"eval_qasc_pairs_steps_per_second": 4.129,
"step": 958
},
{
"epoch": 0.15025094102885822,
"eval_openbookqa_pairs_loss": 5.005772590637207,
"eval_openbookqa_pairs_runtime": 1.0415,
"eval_openbookqa_pairs_samples_per_second": 192.037,
"eval_openbookqa_pairs_steps_per_second": 4.801,
"step": 958
},
{
"epoch": 0.15025094102885822,
"eval_msmarco_pairs_loss": 4.574879169464111,
"eval_msmarco_pairs_runtime": 2.527,
"eval_msmarco_pairs_samples_per_second": 79.146,
"eval_msmarco_pairs_steps_per_second": 1.979,
"step": 958
},
{
"epoch": 0.15025094102885822,
"eval_nq_pairs_loss": 5.281248569488525,
"eval_nq_pairs_runtime": 5.6503,
"eval_nq_pairs_samples_per_second": 35.397,
"eval_nq_pairs_steps_per_second": 0.885,
"step": 958
},
{
"epoch": 0.15025094102885822,
"eval_trivia_pairs_loss": 4.913428783416748,
"eval_trivia_pairs_runtime": 9.0564,
"eval_trivia_pairs_samples_per_second": 22.084,
"eval_trivia_pairs_steps_per_second": 0.552,
"step": 958
},
{
"epoch": 0.15025094102885822,
"eval_quora_pairs_loss": 0.9212128520011902,
"eval_quora_pairs_runtime": 0.6293,
"eval_quora_pairs_samples_per_second": 317.839,
"eval_quora_pairs_steps_per_second": 7.946,
"step": 958
},
{
"epoch": 0.15025094102885822,
"eval_gooaq_pairs_loss": 3.932173490524292,
"eval_gooaq_pairs_runtime": 1.6066,
"eval_gooaq_pairs_samples_per_second": 124.483,
"eval_gooaq_pairs_steps_per_second": 3.112,
"step": 958
},
{
"epoch": 0.15025094102885822,
"eval_mrpc_pairs_loss": 1.0853501558303833,
"eval_mrpc_pairs_runtime": 0.2402,
"eval_mrpc_pairs_samples_per_second": 832.56,
"eval_mrpc_pairs_steps_per_second": 20.814,
"step": 958
},
{
"epoch": 0.15056461731493098,
"grad_norm": 28.37123680114746,
"learning_rate": 6.982434127979924e-06,
"loss": 5.7748,
"step": 960
},
{
"epoch": 0.15809284818067754,
"grad_norm": 26.708221435546875,
"learning_rate": 7.33375156838143e-06,
"loss": 4.8728,
"step": 1008
},
{
"epoch": 0.1656210790464241,
"grad_norm": 26.786447525024414,
"learning_rate": 7.685069008782934e-06,
"loss": 4.7375,
"step": 1056
},
{
"epoch": 0.17314930991217065,
"grad_norm": 26.215879440307617,
"learning_rate": 8.03638644918444e-06,
"loss": 4.6766,
"step": 1104
},
{
"epoch": 0.1806775407779172,
"grad_norm": 35.618831634521484,
"learning_rate": 8.387703889585947e-06,
"loss": 4.3209,
"step": 1152
},
{
"epoch": 0.18820577164366373,
"grad_norm": 37.166072845458984,
"learning_rate": 8.739021329987453e-06,
"loss": 3.7761,
"step": 1200
},
{
"epoch": 0.19573400250941028,
"grad_norm": 35.78367233276367,
"learning_rate": 9.090338770388957e-06,
"loss": 4.2161,
"step": 1248
},
{
"epoch": 0.20326223337515684,
"grad_norm": 36.299678802490234,
"learning_rate": 9.441656210790464e-06,
"loss": 4.9089,
"step": 1296
},
{
"epoch": 0.2107904642409034,
"grad_norm": 18.610933303833008,
"learning_rate": 9.792973651191968e-06,
"loss": 4.3406,
"step": 1344
},
{
"epoch": 0.21831869510664995,
"grad_norm": 9.592538833618164,
"learning_rate": 1.0144291091593475e-05,
"loss": 3.5664,
"step": 1392
},
{
"epoch": 0.22537641154328733,
"eval_nli-pairs_loss": 3.2245519161224365,
"eval_nli-pairs_runtime": 4.0436,
"eval_nli-pairs_samples_per_second": 49.461,
"eval_nli-pairs_steps_per_second": 1.237,
"eval_sts-test_pearson_cosine": 0.7002978854888552,
"eval_sts-test_pearson_dot": 0.5685392445320393,
"eval_sts-test_pearson_euclidean": 0.6963744527231541,
"eval_sts-test_pearson_manhattan": 0.7050517306003169,
"eval_sts-test_pearson_max": 0.7050517306003169,
"eval_sts-test_spearman_cosine": 0.6718756239728468,
"eval_sts-test_spearman_dot": 0.5416448961602434,
"eval_sts-test_spearman_euclidean": 0.6742379556154348,
"eval_sts-test_spearman_manhattan": 0.6824201536078427,
"eval_sts-test_spearman_max": 0.6824201536078427,
"step": 1437
},
{
"epoch": 0.22537641154328733,
"eval_vitaminc-pairs_loss": 6.715206623077393,
"eval_vitaminc-pairs_runtime": 1.4251,
"eval_vitaminc-pairs_samples_per_second": 116.481,
"eval_vitaminc-pairs_steps_per_second": 2.807,
"step": 1437
},
{
"epoch": 0.22537641154328733,
"eval_sts-label_loss": 4.016364097595215,
"eval_sts-label_runtime": 0.4049,
"eval_sts-label_samples_per_second": 493.95,
"eval_sts-label_steps_per_second": 12.349,
"step": 1437
},
{
"epoch": 0.22537641154328733,
"eval_qnli-contrastive_loss": 1.999517560005188,
"eval_qnli-contrastive_runtime": 0.2804,
"eval_qnli-contrastive_samples_per_second": 713.282,
"eval_qnli-contrastive_steps_per_second": 17.832,
"step": 1437
},
{
"epoch": 0.22537641154328733,
"eval_scitail-pairs-qa_loss": 1.0403239727020264,
"eval_scitail-pairs-qa_runtime": 1.0483,
"eval_scitail-pairs-qa_samples_per_second": 190.793,
"eval_scitail-pairs-qa_steps_per_second": 4.77,
"step": 1437
},
{
"epoch": 0.22537641154328733,
"eval_scitail-pairs-pos_loss": 1.9232473373413086,
"eval_scitail-pairs-pos_runtime": 2.3447,
"eval_scitail-pairs-pos_samples_per_second": 85.298,
"eval_scitail-pairs-pos_steps_per_second": 2.132,
"step": 1437
},
{
"epoch": 0.22537641154328733,
"eval_xsum-pairs_loss": 1.6821197271347046,
"eval_xsum-pairs_runtime": 1.0422,
"eval_xsum-pairs_samples_per_second": 191.901,
"eval_xsum-pairs_steps_per_second": 4.798,
"step": 1437
},
{
"epoch": 0.22537641154328733,
"eval_compression-pairs_loss": 1.1713249683380127,
"eval_compression-pairs_runtime": 0.2392,
"eval_compression-pairs_samples_per_second": 836.05,
"eval_compression-pairs_steps_per_second": 20.901,
"step": 1437
},
{
"epoch": 0.22537641154328733,
"eval_sciq_pairs_loss": 9.443825721740723,
"eval_sciq_pairs_runtime": 8.9916,
"eval_sciq_pairs_samples_per_second": 22.243,
"eval_sciq_pairs_steps_per_second": 0.556,
"step": 1437
},
{
"epoch": 0.22537641154328733,
"eval_qasc_pairs_loss": 2.9044029712677,
"eval_qasc_pairs_runtime": 1.2182,
"eval_qasc_pairs_samples_per_second": 164.182,
"eval_qasc_pairs_steps_per_second": 4.105,
"step": 1437
},
{
"epoch": 0.22537641154328733,
"eval_openbookqa_pairs_loss": 4.360418796539307,
"eval_openbookqa_pairs_runtime": 1.0522,
"eval_openbookqa_pairs_samples_per_second": 190.077,
"eval_openbookqa_pairs_steps_per_second": 4.752,
"step": 1437
},
{
"epoch": 0.22537641154328733,
"eval_msmarco_pairs_loss": 3.516049861907959,
"eval_msmarco_pairs_runtime": 2.5595,
"eval_msmarco_pairs_samples_per_second": 78.139,
"eval_msmarco_pairs_steps_per_second": 1.953,
"step": 1437
},
{
"epoch": 0.22537641154328733,
"eval_nq_pairs_loss": 4.016308784484863,
"eval_nq_pairs_runtime": 5.6561,
"eval_nq_pairs_samples_per_second": 35.36,
"eval_nq_pairs_steps_per_second": 0.884,
"step": 1437
},
{
"epoch": 0.22537641154328733,
"eval_trivia_pairs_loss": 3.781872272491455,
"eval_trivia_pairs_runtime": 9.0801,
"eval_trivia_pairs_samples_per_second": 22.026,
"eval_trivia_pairs_steps_per_second": 0.551,
"step": 1437
},
{
"epoch": 0.22537641154328733,
"eval_quora_pairs_loss": 0.8747495412826538,
"eval_quora_pairs_runtime": 0.6229,
"eval_quora_pairs_samples_per_second": 321.076,
"eval_quora_pairs_steps_per_second": 8.027,
"step": 1437
},
{
"epoch": 0.22537641154328733,
"eval_gooaq_pairs_loss": 3.0769765377044678,
"eval_gooaq_pairs_runtime": 1.552,
"eval_gooaq_pairs_samples_per_second": 128.863,
"eval_gooaq_pairs_steps_per_second": 3.222,
"step": 1437
},
{
"epoch": 0.22537641154328733,
"eval_mrpc_pairs_loss": 0.7370794415473938,
"eval_mrpc_pairs_runtime": 0.2401,
"eval_mrpc_pairs_samples_per_second": 832.867,
"eval_mrpc_pairs_steps_per_second": 20.822,
"step": 1437
},
{
"epoch": 0.2258469259723965,
"grad_norm": 29.73522186279297,
"learning_rate": 1.049560853199498e-05,
"loss": 4.7194,
"step": 1440
},
{
"epoch": 0.23337515683814303,
"grad_norm": 30.467117309570312,
"learning_rate": 1.0846925972396486e-05,
"loss": 3.6345,
"step": 1488
},
{
"epoch": 0.24090338770388958,
"grad_norm": 24.454021453857422,
"learning_rate": 1.1198243412797992e-05,
"loss": 3.5947,
"step": 1536
},
{
"epoch": 0.24843161856963614,
"grad_norm": 20.165475845336914,
"learning_rate": 1.1549560853199497e-05,
"loss": 4.0526,
"step": 1584
},
{
"epoch": 0.2559598494353827,
"grad_norm": 34.79319381713867,
"learning_rate": 1.1900878293601003e-05,
"loss": 3.7962,
"step": 1632
},
{
"epoch": 0.26348808030112925,
"grad_norm": 127.97925567626953,
"learning_rate": 1.2252195734002508e-05,
"loss": 4.1927,
"step": 1680
},
{
"epoch": 0.2710163111668758,
"grad_norm": 27.80243682861328,
"learning_rate": 1.2603513174404014e-05,
"loss": 3.6351,
"step": 1728
},
{
"epoch": 0.27854454203262236,
"grad_norm": 31.81105613708496,
"learning_rate": 1.295483061480552e-05,
"loss": 3.4256,
"step": 1776
},
{
"epoch": 0.2860727728983689,
"grad_norm": 32.932865142822266,
"learning_rate": 1.3306148055207025e-05,
"loss": 3.3175,
"step": 1824
},
{
"epoch": 0.2936010037641154,
"grad_norm": 31.197385787963867,
"learning_rate": 1.365746549560853e-05,
"loss": 3.4984,
"step": 1872
},
{
"epoch": 0.30050188205771644,
"eval_nli-pairs_loss": 2.852742910385132,
"eval_nli-pairs_runtime": 4.1529,
"eval_nli-pairs_samples_per_second": 48.16,
"eval_nli-pairs_steps_per_second": 1.204,
"eval_sts-test_pearson_cosine": 0.7132313507241694,
"eval_sts-test_pearson_dot": 0.559846529627866,
"eval_sts-test_pearson_euclidean": 0.7145939583366395,
"eval_sts-test_pearson_manhattan": 0.724552982808093,
"eval_sts-test_pearson_max": 0.724552982808093,
"eval_sts-test_spearman_cosine": 0.6912239915389706,
"eval_sts-test_spearman_dot": 0.5394217029355446,
"eval_sts-test_spearman_euclidean": 0.6946616748545426,
"eval_sts-test_spearman_manhattan": 0.70491424059339,
"eval_sts-test_spearman_max": 0.70491424059339,
"step": 1916
},
{
"epoch": 0.30050188205771644,
"eval_vitaminc-pairs_loss": 6.633151054382324,
"eval_vitaminc-pairs_runtime": 1.4454,
"eval_vitaminc-pairs_samples_per_second": 114.849,
"eval_vitaminc-pairs_steps_per_second": 2.767,
"step": 1916
},
{
"epoch": 0.30050188205771644,
"eval_sts-label_loss": 3.8717281818389893,
"eval_sts-label_runtime": 0.4016,
"eval_sts-label_samples_per_second": 498.049,
"eval_sts-label_steps_per_second": 12.451,
"step": 1916
},
{
"epoch": 0.30050188205771644,
"eval_qnli-contrastive_loss": 1.4170150756835938,
"eval_qnli-contrastive_runtime": 0.2814,
"eval_qnli-contrastive_samples_per_second": 710.85,
"eval_qnli-contrastive_steps_per_second": 17.771,
"step": 1916
},
{
"epoch": 0.30050188205771644,
"eval_scitail-pairs-qa_loss": 0.6900365948677063,
"eval_scitail-pairs-qa_runtime": 1.0611,
"eval_scitail-pairs-qa_samples_per_second": 188.492,
"eval_scitail-pairs-qa_steps_per_second": 4.712,
"step": 1916
},
{
"epoch": 0.30050188205771644,
"eval_scitail-pairs-pos_loss": 1.352358102798462,
"eval_scitail-pairs-pos_runtime": 2.3596,
"eval_scitail-pairs-pos_samples_per_second": 84.761,
"eval_scitail-pairs-pos_steps_per_second": 2.119,
"step": 1916
},
{
"epoch": 0.30050188205771644,
"eval_xsum-pairs_loss": 1.376610517501831,
"eval_xsum-pairs_runtime": 1.0393,
"eval_xsum-pairs_samples_per_second": 192.443,
"eval_xsum-pairs_steps_per_second": 4.811,
"step": 1916
},
{
"epoch": 0.30050188205771644,
"eval_compression-pairs_loss": 0.871735692024231,
"eval_compression-pairs_runtime": 0.2351,
"eval_compression-pairs_samples_per_second": 850.579,
"eval_compression-pairs_steps_per_second": 21.264,
"step": 1916
},
{
"epoch": 0.30050188205771644,
"eval_sciq_pairs_loss": 9.191713333129883,
"eval_sciq_pairs_runtime": 9.1572,
"eval_sciq_pairs_samples_per_second": 21.841,
"eval_sciq_pairs_steps_per_second": 0.546,
"step": 1916
},
{
"epoch": 0.30050188205771644,
"eval_qasc_pairs_loss": 2.369694709777832,
"eval_qasc_pairs_runtime": 1.2239,
"eval_qasc_pairs_samples_per_second": 163.415,
"eval_qasc_pairs_steps_per_second": 4.085,
"step": 1916
},
{
"epoch": 0.30050188205771644,
"eval_openbookqa_pairs_loss": 3.9601967334747314,
"eval_openbookqa_pairs_runtime": 1.0681,
"eval_openbookqa_pairs_samples_per_second": 187.247,
"eval_openbookqa_pairs_steps_per_second": 4.681,
"step": 1916
},
{
"epoch": 0.30050188205771644,
"eval_msmarco_pairs_loss": 3.0808801651000977,
"eval_msmarco_pairs_runtime": 2.5507,
"eval_msmarco_pairs_samples_per_second": 78.409,
"eval_msmarco_pairs_steps_per_second": 1.96,
"step": 1916
},
{
"epoch": 0.30050188205771644,
"eval_nq_pairs_loss": 3.4922549724578857,
"eval_nq_pairs_runtime": 5.7154,
"eval_nq_pairs_samples_per_second": 34.993,
"eval_nq_pairs_steps_per_second": 0.875,
"step": 1916
},
{
"epoch": 0.30050188205771644,
"eval_trivia_pairs_loss": 3.4910638332366943,
"eval_trivia_pairs_runtime": 9.1195,
"eval_trivia_pairs_samples_per_second": 21.931,
"eval_trivia_pairs_steps_per_second": 0.548,
"step": 1916
},
{
"epoch": 0.30050188205771644,
"eval_quora_pairs_loss": 0.833874523639679,
"eval_quora_pairs_runtime": 0.6419,
"eval_quora_pairs_samples_per_second": 311.554,
"eval_quora_pairs_steps_per_second": 7.789,
"step": 1916
},
{
"epoch": 0.30050188205771644,
"eval_gooaq_pairs_loss": 2.622526168823242,
"eval_gooaq_pairs_runtime": 1.5751,
"eval_gooaq_pairs_samples_per_second": 126.977,
"eval_gooaq_pairs_steps_per_second": 3.174,
"step": 1916
},
{
"epoch": 0.30050188205771644,
"eval_mrpc_pairs_loss": 0.4888114929199219,
"eval_mrpc_pairs_runtime": 0.2398,
"eval_mrpc_pairs_samples_per_second": 833.994,
"eval_mrpc_pairs_steps_per_second": 20.85,
"step": 1916
},
{
"epoch": 0.30112923462986196,
"grad_norm": 6.916851997375488,
"learning_rate": 1.4008782936010036e-05,
"loss": 2.7233,
"step": 1920
},
{
"epoch": 0.3086574654956085,
"grad_norm": 17.678085327148438,
"learning_rate": 1.4360100376411543e-05,
"loss": 3.6816,
"step": 1968
},
{
"epoch": 0.3161856963613551,
"grad_norm": 92.62138366699219,
"learning_rate": 1.4711417816813047e-05,
"loss": 3.3232,
"step": 2016
},
{
"epoch": 0.3237139272271016,
"grad_norm": 27.2542781829834,
"learning_rate": 1.5062735257214554e-05,
"loss": 3.3469,
"step": 2064
},
{
"epoch": 0.3312421580928482,
"grad_norm": 6.005978584289551,
"learning_rate": 1.5414052697616058e-05,
"loss": 3.7509,
"step": 2112
},
{
"epoch": 0.33877038895859474,
"grad_norm": 16.488624572753906,
"learning_rate": 1.5765370138017566e-05,
"loss": 3.1811,
"step": 2160
},
{
"epoch": 0.3462986198243413,
"grad_norm": 11.462204933166504,
"learning_rate": 1.611668757841907e-05,
"loss": 3.3341,
"step": 2208
},
{
"epoch": 0.35382685069008785,
"grad_norm": 33.485206604003906,
"learning_rate": 1.6468005018820577e-05,
"loss": 2.764,
"step": 2256
},
{
"epoch": 0.3613550815558344,
"grad_norm": 25.066240310668945,
"learning_rate": 1.681932245922208e-05,
"loss": 3.6488,
"step": 2304
},
{
"epoch": 0.36888331242158096,
"grad_norm": 28.305265426635742,
"learning_rate": 1.7170639899623588e-05,
"loss": 2.721,
"step": 2352
},
{
"epoch": 0.3756273525721455,
"eval_nli-pairs_loss": 2.527458667755127,
"eval_nli-pairs_runtime": 4.1153,
"eval_nli-pairs_samples_per_second": 48.599,
"eval_nli-pairs_steps_per_second": 1.215,
"eval_sts-test_pearson_cosine": 0.7258900302408404,
"eval_sts-test_pearson_dot": 0.5655223839113195,
"eval_sts-test_pearson_euclidean": 0.7228747263710285,
"eval_sts-test_pearson_manhattan": 0.732591374373909,
"eval_sts-test_pearson_max": 0.732591374373909,
"eval_sts-test_spearman_cosine": 0.707910346125958,
"eval_sts-test_spearman_dot": 0.5482635095738919,
"eval_sts-test_spearman_euclidean": 0.7064759533156177,
"eval_sts-test_spearman_manhattan": 0.7166423493246757,
"eval_sts-test_spearman_max": 0.7166423493246757,
"step": 2395
},
{
"epoch": 0.3756273525721455,
"eval_vitaminc-pairs_loss": 6.437549114227295,
"eval_vitaminc-pairs_runtime": 1.4278,
"eval_vitaminc-pairs_samples_per_second": 116.261,
"eval_vitaminc-pairs_steps_per_second": 2.801,
"step": 2395
},
{
"epoch": 0.3756273525721455,
"eval_sts-label_loss": 4.1980671882629395,
"eval_sts-label_runtime": 0.3956,
"eval_sts-label_samples_per_second": 505.555,
"eval_sts-label_steps_per_second": 12.639,
"step": 2395
},
{
"epoch": 0.3756273525721455,
"eval_qnli-contrastive_loss": 1.0682133436203003,
"eval_qnli-contrastive_runtime": 0.2789,
"eval_qnli-contrastive_samples_per_second": 717.152,
"eval_qnli-contrastive_steps_per_second": 17.929,
"step": 2395
},
{
"epoch": 0.3756273525721455,
"eval_scitail-pairs-qa_loss": 0.5046552419662476,
"eval_scitail-pairs-qa_runtime": 1.0451,
"eval_scitail-pairs-qa_samples_per_second": 191.365,
"eval_scitail-pairs-qa_steps_per_second": 4.784,
"step": 2395
},
{
"epoch": 0.3756273525721455,
"eval_scitail-pairs-pos_loss": 1.1998459100723267,
"eval_scitail-pairs-pos_runtime": 2.3442,
"eval_scitail-pairs-pos_samples_per_second": 85.316,
"eval_scitail-pairs-pos_steps_per_second": 2.133,
"step": 2395
},
{
"epoch": 0.3756273525721455,
"eval_xsum-pairs_loss": 1.1817097663879395,
"eval_xsum-pairs_runtime": 1.0372,
"eval_xsum-pairs_samples_per_second": 192.835,
"eval_xsum-pairs_steps_per_second": 4.821,
"step": 2395
},
{
"epoch": 0.3756273525721455,
"eval_compression-pairs_loss": 0.6974765062332153,
"eval_compression-pairs_runtime": 0.2369,
"eval_compression-pairs_samples_per_second": 844.401,
"eval_compression-pairs_steps_per_second": 21.11,
"step": 2395
},
{
"epoch": 0.3756273525721455,
"eval_sciq_pairs_loss": 8.970888137817383,
"eval_sciq_pairs_runtime": 9.0441,
"eval_sciq_pairs_samples_per_second": 22.114,
"eval_sciq_pairs_steps_per_second": 0.553,
"step": 2395
},
{
"epoch": 0.3756273525721455,
"eval_qasc_pairs_loss": 1.9235339164733887,
"eval_qasc_pairs_runtime": 1.2061,
"eval_qasc_pairs_samples_per_second": 165.828,
"eval_qasc_pairs_steps_per_second": 4.146,
"step": 2395
},
{
"epoch": 0.3756273525721455,
"eval_openbookqa_pairs_loss": 3.6225194931030273,
"eval_openbookqa_pairs_runtime": 1.0455,
"eval_openbookqa_pairs_samples_per_second": 191.296,
"eval_openbookqa_pairs_steps_per_second": 4.782,
"step": 2395
},
{
"epoch": 0.3756273525721455,
"eval_msmarco_pairs_loss": 2.664341926574707,
"eval_msmarco_pairs_runtime": 2.5305,
"eval_msmarco_pairs_samples_per_second": 79.036,
"eval_msmarco_pairs_steps_per_second": 1.976,
"step": 2395
},
{
"epoch": 0.3756273525721455,
"eval_nq_pairs_loss": 3.055206298828125,
"eval_nq_pairs_runtime": 5.6527,
"eval_nq_pairs_samples_per_second": 35.381,
"eval_nq_pairs_steps_per_second": 0.885,
"step": 2395
},
{
"epoch": 0.3756273525721455,
"eval_trivia_pairs_loss": 2.9497525691986084,
"eval_trivia_pairs_runtime": 9.0334,
"eval_trivia_pairs_samples_per_second": 22.14,
"eval_trivia_pairs_steps_per_second": 0.554,
"step": 2395
},
{
"epoch": 0.3756273525721455,
"eval_quora_pairs_loss": 0.7771684527397156,
"eval_quora_pairs_runtime": 0.626,
"eval_quora_pairs_samples_per_second": 319.495,
"eval_quora_pairs_steps_per_second": 7.987,
"step": 2395
},
{
"epoch": 0.3756273525721455,
"eval_gooaq_pairs_loss": 2.266879081726074,
"eval_gooaq_pairs_runtime": 1.5425,
"eval_gooaq_pairs_samples_per_second": 129.664,
"eval_gooaq_pairs_steps_per_second": 3.242,
"step": 2395
},
{
"epoch": 0.3756273525721455,
"eval_mrpc_pairs_loss": 0.36913084983825684,
"eval_mrpc_pairs_runtime": 0.2383,
"eval_mrpc_pairs_samples_per_second": 839.153,
"eval_mrpc_pairs_steps_per_second": 20.979,
"step": 2395
},
{
"epoch": 0.37641154328732745,
"grad_norm": 36.60768127441406,
"learning_rate": 1.752195734002509e-05,
"loss": 3.3609,
"step": 2400
},
{
"epoch": 0.383939774153074,
"grad_norm": 24.15782928466797,
"learning_rate": 1.7873274780426595e-05,
"loss": 2.6252,
"step": 2448
},
{
"epoch": 0.39146800501882056,
"grad_norm": 7.509932041168213,
"learning_rate": 1.8224592220828106e-05,
"loss": 3.5142,
"step": 2496
},
{
"epoch": 0.3989962358845671,
"grad_norm": 29.380950927734375,
"learning_rate": 1.857590966122961e-05,
"loss": 4.0597,
"step": 2544
},
{
"epoch": 0.4065244667503137,
"grad_norm": 28.593975067138672,
"learning_rate": 1.8927227101631114e-05,
"loss": 2.8512,
"step": 2592
},
{
"epoch": 0.41405269761606023,
"grad_norm": 21.228628158569336,
"learning_rate": 1.927854454203262e-05,
"loss": 2.717,
"step": 2640
},
{
"epoch": 0.4215809284818068,
"grad_norm": 43.00386047363281,
"learning_rate": 1.962986198243413e-05,
"loss": 3.4717,
"step": 2688
},
{
"epoch": 0.42910915934755334,
"grad_norm": 25.004785537719727,
"learning_rate": 1.9981179422835632e-05,
"loss": 3.1105,
"step": 2736
},
{
"epoch": 0.4366373902132999,
"grad_norm": 7.555154323577881,
"learning_rate": 2.0332496863237136e-05,
"loss": 2.7798,
"step": 2784
},
{
"epoch": 0.44416562107904645,
"grad_norm": 30.839733123779297,
"learning_rate": 2.0683814303638643e-05,
"loss": 3.3606,
"step": 2832
},
{
"epoch": 0.45075282308657466,
"eval_nli-pairs_loss": 2.284590721130371,
"eval_nli-pairs_runtime": 4.0714,
"eval_nli-pairs_samples_per_second": 49.123,
"eval_nli-pairs_steps_per_second": 1.228,
"eval_sts-test_pearson_cosine": 0.7382507781851606,
"eval_sts-test_pearson_dot": 0.5710221319397019,
"eval_sts-test_pearson_euclidean": 0.7307583601561211,
"eval_sts-test_pearson_manhattan": 0.7394202696141936,
"eval_sts-test_pearson_max": 0.7394202696141936,
"eval_sts-test_spearman_cosine": 0.7211579109789371,
"eval_sts-test_spearman_dot": 0.5515579746967598,
"eval_sts-test_spearman_euclidean": 0.7142073811971875,
"eval_sts-test_spearman_manhattan": 0.7240537218564107,
"eval_sts-test_spearman_max": 0.7240537218564107,
"step": 2874
},
{
"epoch": 0.45075282308657466,
"eval_vitaminc-pairs_loss": 6.35264253616333,
"eval_vitaminc-pairs_runtime": 1.4349,
"eval_vitaminc-pairs_samples_per_second": 115.687,
"eval_vitaminc-pairs_steps_per_second": 2.788,
"step": 2874
},
{
"epoch": 0.45075282308657466,
"eval_sts-label_loss": 4.186042308807373,
"eval_sts-label_runtime": 0.3983,
"eval_sts-label_samples_per_second": 502.129,
"eval_sts-label_steps_per_second": 12.553,
"step": 2874
},
{
"epoch": 0.45075282308657466,
"eval_qnli-contrastive_loss": 0.781445324420929,
"eval_qnli-contrastive_runtime": 0.2765,
"eval_qnli-contrastive_samples_per_second": 723.448,
"eval_qnli-contrastive_steps_per_second": 18.086,
"step": 2874
},
{
"epoch": 0.45075282308657466,
"eval_scitail-pairs-qa_loss": 0.4217279851436615,
"eval_scitail-pairs-qa_runtime": 1.0438,
"eval_scitail-pairs-qa_samples_per_second": 191.612,
"eval_scitail-pairs-qa_steps_per_second": 4.79,
"step": 2874
},
{
"epoch": 0.45075282308657466,
"eval_scitail-pairs-pos_loss": 1.051362156867981,
"eval_scitail-pairs-pos_runtime": 2.3425,
"eval_scitail-pairs-pos_samples_per_second": 85.379,
"eval_scitail-pairs-pos_steps_per_second": 2.134,
"step": 2874
},
{
"epoch": 0.45075282308657466,
"eval_xsum-pairs_loss": 1.0554753541946411,
"eval_xsum-pairs_runtime": 1.044,
"eval_xsum-pairs_samples_per_second": 191.573,
"eval_xsum-pairs_steps_per_second": 4.789,
"step": 2874
},
{
"epoch": 0.45075282308657466,
"eval_compression-pairs_loss": 0.6035106778144836,
"eval_compression-pairs_runtime": 0.241,
"eval_compression-pairs_samples_per_second": 830.038,
"eval_compression-pairs_steps_per_second": 20.751,
"step": 2874
},
{
"epoch": 0.45075282308657466,
"eval_sciq_pairs_loss": 8.811105728149414,
"eval_sciq_pairs_runtime": 9.0357,
"eval_sciq_pairs_samples_per_second": 22.134,
"eval_sciq_pairs_steps_per_second": 0.553,
"step": 2874
},
{
"epoch": 0.45075282308657466,
"eval_qasc_pairs_loss": 1.615903377532959,
"eval_qasc_pairs_runtime": 1.214,
"eval_qasc_pairs_samples_per_second": 164.746,
"eval_qasc_pairs_steps_per_second": 4.119,
"step": 2874
},
{
"epoch": 0.45075282308657466,
"eval_openbookqa_pairs_loss": 3.4049320220947266,
"eval_openbookqa_pairs_runtime": 1.0554,
"eval_openbookqa_pairs_samples_per_second": 189.509,
"eval_openbookqa_pairs_steps_per_second": 4.738,
"step": 2874
},
{
"epoch": 0.45075282308657466,
"eval_msmarco_pairs_loss": 2.3909060955047607,
"eval_msmarco_pairs_runtime": 2.5301,
"eval_msmarco_pairs_samples_per_second": 79.048,
"eval_msmarco_pairs_steps_per_second": 1.976,
"step": 2874
},
{
"epoch": 0.45075282308657466,
"eval_nq_pairs_loss": 2.794445753097534,
"eval_nq_pairs_runtime": 5.6752,
"eval_nq_pairs_samples_per_second": 35.241,
"eval_nq_pairs_steps_per_second": 0.881,
"step": 2874
},
{
"epoch": 0.45075282308657466,
"eval_trivia_pairs_loss": 2.753361701965332,
"eval_trivia_pairs_runtime": 9.0766,
"eval_trivia_pairs_samples_per_second": 22.035,
"eval_trivia_pairs_steps_per_second": 0.551,
"step": 2874
},
{
"epoch": 0.45075282308657466,
"eval_quora_pairs_loss": 0.205492302775383,
"eval_quora_pairs_runtime": 0.6182,
"eval_quora_pairs_samples_per_second": 323.536,
"eval_quora_pairs_steps_per_second": 8.088,
"step": 2874
},
{
"epoch": 0.45075282308657466,
"eval_gooaq_pairs_loss": 2.038878917694092,
"eval_gooaq_pairs_runtime": 1.5488,
"eval_gooaq_pairs_samples_per_second": 129.134,
"eval_gooaq_pairs_steps_per_second": 3.228,
"step": 2874
},
{
"epoch": 0.45075282308657466,
"eval_mrpc_pairs_loss": 0.3230588436126709,
"eval_mrpc_pairs_runtime": 0.2358,
"eval_mrpc_pairs_samples_per_second": 848.229,
"eval_mrpc_pairs_steps_per_second": 21.206,
"step": 2874
},
{
"epoch": 0.451693851944793,
"grad_norm": 5.271574020385742,
"learning_rate": 2.103513174404015e-05,
"loss": 2.6918,
"step": 2880
},
{
"epoch": 0.4592220828105395,
"grad_norm": 21.954103469848633,
"learning_rate": 2.1386449184441654e-05,
"loss": 2.8354,
"step": 2928
},
{
"epoch": 0.46675031367628605,
"grad_norm": 28.671293258666992,
"learning_rate": 2.173776662484316e-05,
"loss": 2.9499,
"step": 2976
},
{
"epoch": 0.4742785445420326,
"grad_norm": 26.562397003173828,
"learning_rate": 2.2089084065244666e-05,
"loss": 2.6211,
"step": 3024
},
{
"epoch": 0.48180677540777916,
"grad_norm": 48.511756896972656,
"learning_rate": 2.2440401505646173e-05,
"loss": 3.3356,
"step": 3072
},
{
"epoch": 0.4893350062735257,
"grad_norm": 46.71563720703125,
"learning_rate": 2.2791718946047677e-05,
"loss": 2.846,
"step": 3120
},
{
"epoch": 0.4968632371392723,
"grad_norm": 24.524322509765625,
"learning_rate": 2.3143036386449184e-05,
"loss": 2.4866,
"step": 3168
},
{
"epoch": 0.5043914680050188,
"grad_norm": 85.22843933105469,
"learning_rate": 2.3494353826850688e-05,
"loss": 2.6334,
"step": 3216
},
{
"epoch": 0.5119196988707654,
"grad_norm": 28.435443878173828,
"learning_rate": 2.384567126725219e-05,
"loss": 2.6118,
"step": 3264
},
{
"epoch": 0.5194479297365119,
"grad_norm": 21.590103149414062,
"learning_rate": 2.41969887076537e-05,
"loss": 2.5833,
"step": 3312
},
{
"epoch": 0.5258782936010038,
"eval_nli-pairs_loss": 2.0752949714660645,
"eval_nli-pairs_runtime": 4.0304,
"eval_nli-pairs_samples_per_second": 49.623,
"eval_nli-pairs_steps_per_second": 1.241,
"eval_sts-test_pearson_cosine": 0.7401847199967786,
"eval_sts-test_pearson_dot": 0.5441501995975192,
"eval_sts-test_pearson_euclidean": 0.7344996320188322,
"eval_sts-test_pearson_manhattan": 0.7394640598472787,
"eval_sts-test_pearson_max": 0.7401847199967786,
"eval_sts-test_spearman_cosine": 0.7300085598018916,
"eval_sts-test_spearman_dot": 0.5241747185593542,
"eval_sts-test_spearman_euclidean": 0.7194131601167465,
"eval_sts-test_spearman_manhattan": 0.726961581928453,
"eval_sts-test_spearman_max": 0.7300085598018916,
"step": 3353
},
{
"epoch": 0.5258782936010038,
"eval_vitaminc-pairs_loss": 6.441956996917725,
"eval_vitaminc-pairs_runtime": 1.4416,
"eval_vitaminc-pairs_samples_per_second": 115.149,
"eval_vitaminc-pairs_steps_per_second": 2.775,
"step": 3353
},
{
"epoch": 0.5258782936010038,
"eval_sts-label_loss": 4.200085639953613,
"eval_sts-label_runtime": 0.3949,
"eval_sts-label_samples_per_second": 506.436,
"eval_sts-label_steps_per_second": 12.661,
"step": 3353
},
{
"epoch": 0.5258782936010038,
"eval_qnli-contrastive_loss": 0.5195684432983398,
"eval_qnli-contrastive_runtime": 0.2809,
"eval_qnli-contrastive_samples_per_second": 712.107,
"eval_qnli-contrastive_steps_per_second": 17.803,
"step": 3353
},
{
"epoch": 0.5258782936010038,
"eval_scitail-pairs-qa_loss": 0.35189124941825867,
"eval_scitail-pairs-qa_runtime": 1.0578,
"eval_scitail-pairs-qa_samples_per_second": 189.064,
"eval_scitail-pairs-qa_steps_per_second": 4.727,
"step": 3353
},
{
"epoch": 0.5258782936010038,
"eval_scitail-pairs-pos_loss": 0.8873756527900696,
"eval_scitail-pairs-pos_runtime": 2.4029,
"eval_scitail-pairs-pos_samples_per_second": 83.232,
"eval_scitail-pairs-pos_steps_per_second": 2.081,
"step": 3353
},
{
"epoch": 0.5258782936010038,
"eval_xsum-pairs_loss": 0.939339280128479,
"eval_xsum-pairs_runtime": 1.041,
"eval_xsum-pairs_samples_per_second": 192.121,
"eval_xsum-pairs_steps_per_second": 4.803,
"step": 3353
},
{
"epoch": 0.5258782936010038,
"eval_compression-pairs_loss": 0.5007131695747375,
"eval_compression-pairs_runtime": 0.2338,
"eval_compression-pairs_samples_per_second": 855.479,
"eval_compression-pairs_steps_per_second": 21.387,
"step": 3353
},
{
"epoch": 0.5258782936010038,
"eval_sciq_pairs_loss": 8.558987617492676,
"eval_sciq_pairs_runtime": 9.0984,
"eval_sciq_pairs_samples_per_second": 21.982,
"eval_sciq_pairs_steps_per_second": 0.55,
"step": 3353
},
{
"epoch": 0.5258782936010038,
"eval_qasc_pairs_loss": 1.4318852424621582,
"eval_qasc_pairs_runtime": 1.2286,
"eval_qasc_pairs_samples_per_second": 162.79,
"eval_qasc_pairs_steps_per_second": 4.07,
"step": 3353
},
{
"epoch": 0.5258782936010038,
"eval_openbookqa_pairs_loss": 3.1973114013671875,
"eval_openbookqa_pairs_runtime": 1.0491,
"eval_openbookqa_pairs_samples_per_second": 190.633,
"eval_openbookqa_pairs_steps_per_second": 4.766,
"step": 3353
},
{
"epoch": 0.5258782936010038,
"eval_msmarco_pairs_loss": 2.2080254554748535,
"eval_msmarco_pairs_runtime": 2.5223,
"eval_msmarco_pairs_samples_per_second": 79.294,
"eval_msmarco_pairs_steps_per_second": 1.982,
"step": 3353
},
{
"epoch": 0.5258782936010038,
"eval_nq_pairs_loss": 2.5810558795928955,
"eval_nq_pairs_runtime": 5.6341,
"eval_nq_pairs_samples_per_second": 35.498,
"eval_nq_pairs_steps_per_second": 0.887,
"step": 3353
},
{
"epoch": 0.5258782936010038,
"eval_trivia_pairs_loss": 2.655771255493164,
"eval_trivia_pairs_runtime": 9.0716,
"eval_trivia_pairs_samples_per_second": 22.047,
"eval_trivia_pairs_steps_per_second": 0.551,
"step": 3353
},
{
"epoch": 0.5258782936010038,
"eval_quora_pairs_loss": 0.5028819441795349,
"eval_quora_pairs_runtime": 0.6144,
"eval_quora_pairs_samples_per_second": 325.522,
"eval_quora_pairs_steps_per_second": 8.138,
"step": 3353
},
{
"epoch": 0.5258782936010038,
"eval_gooaq_pairs_loss": 1.8867437839508057,
"eval_gooaq_pairs_runtime": 1.5505,
"eval_gooaq_pairs_samples_per_second": 128.994,
"eval_gooaq_pairs_steps_per_second": 3.225,
"step": 3353
},
{
"epoch": 0.5258782936010038,
"eval_mrpc_pairs_loss": 0.2580638825893402,
"eval_mrpc_pairs_runtime": 0.2364,
"eval_mrpc_pairs_samples_per_second": 846.008,
"eval_mrpc_pairs_steps_per_second": 21.15,
"step": 3353
},
{
"epoch": 0.5269761606022585,
"grad_norm": 2.6962711811065674,
"learning_rate": 2.4548306148055206e-05,
"loss": 2.3251,
"step": 3360
},
{
"epoch": 0.534504391468005,
"grad_norm": 35.47948455810547,
"learning_rate": 2.489962358845671e-05,
"loss": 2.8494,
"step": 3408
},
{
"epoch": 0.5420326223337516,
"grad_norm": 8.13453483581543,
"learning_rate": 2.5250941028858214e-05,
"loss": 2.4009,
"step": 3456
},
{
"epoch": 0.5495608531994981,
"grad_norm": 20.041057586669922,
"learning_rate": 2.560225846925972e-05,
"loss": 2.5952,
"step": 3504
},
{
"epoch": 0.5570890840652447,
"grad_norm": 23.942073822021484,
"learning_rate": 2.595357590966123e-05,
"loss": 2.2798,
"step": 3552
},
{
"epoch": 0.5646173149309912,
"grad_norm": 17.675006866455078,
"learning_rate": 2.6304893350062732e-05,
"loss": 2.308,
"step": 3600
},
{
"epoch": 0.5721455457967378,
"grad_norm": 24.20000457763672,
"learning_rate": 2.6656210790464236e-05,
"loss": 2.122,
"step": 3648
},
{
"epoch": 0.5796737766624843,
"grad_norm": 30.06256866455078,
"learning_rate": 2.7007528230865747e-05,
"loss": 2.7901,
"step": 3696
},
{
"epoch": 0.5872020075282308,
"grad_norm": 22.547115325927734,
"learning_rate": 2.735884567126725e-05,
"loss": 2.0671,
"step": 3744
},
{
"epoch": 0.5947302383939774,
"grad_norm": 34.11716079711914,
"learning_rate": 2.7710163111668754e-05,
"loss": 2.366,
"step": 3792
}
],
"logging_steps": 48,
"max_steps": 19128,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 1913,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 42,
"trial_name": null,
"trial_params": null
}