| { | |
| "best_metric": 0.03607647866010666, | |
| "best_model_checkpoint": "/content/drive/MyDrive/HateSpeech-BETO-cased/checkpoint-1124", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 1124, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03558718861209965, | |
| "grad_norm": 7.08419132232666, | |
| "learning_rate": 2.2271714922049e-07, | |
| "loss": 0.4085, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0711743772241993, | |
| "grad_norm": 23.322711944580078, | |
| "learning_rate": 4.4543429844098e-07, | |
| "loss": 0.3565, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10676156583629894, | |
| "grad_norm": 8.696600914001465, | |
| "learning_rate": 6.6815144766147e-07, | |
| "loss": 0.3482, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1423487544483986, | |
| "grad_norm": 14.429851531982422, | |
| "learning_rate": 8.9086859688196e-07, | |
| "loss": 0.3711, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.17793594306049823, | |
| "grad_norm": 9.41112995147705, | |
| "learning_rate": 1.11358574610245e-06, | |
| "loss": 0.337, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.21352313167259787, | |
| "grad_norm": 12.487126350402832, | |
| "learning_rate": 1.33630289532294e-06, | |
| "loss": 0.3413, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2491103202846975, | |
| "grad_norm": 17.9010009765625, | |
| "learning_rate": 1.55902004454343e-06, | |
| "loss": 0.3154, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2846975088967972, | |
| "grad_norm": 17.09844207763672, | |
| "learning_rate": 1.78173719376392e-06, | |
| "loss": 0.2304, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3202846975088968, | |
| "grad_norm": 19.929523468017578, | |
| "learning_rate": 2.00445434298441e-06, | |
| "loss": 0.308, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.35587188612099646, | |
| "grad_norm": 5.709442615509033, | |
| "learning_rate": 2.2271714922049e-06, | |
| "loss": 0.2692, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3914590747330961, | |
| "grad_norm": 19.828474044799805, | |
| "learning_rate": 2.44988864142539e-06, | |
| "loss": 0.2255, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.42704626334519574, | |
| "grad_norm": 17.53233528137207, | |
| "learning_rate": 2.67260579064588e-06, | |
| "loss": 0.1917, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.4626334519572954, | |
| "grad_norm": 14.940444946289062, | |
| "learning_rate": 2.8953229398663702e-06, | |
| "loss": 0.3019, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.498220640569395, | |
| "grad_norm": 1.711176872253418, | |
| "learning_rate": 3.11804008908686e-06, | |
| "loss": 0.2032, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5338078291814946, | |
| "grad_norm": 7.716080665588379, | |
| "learning_rate": 3.34075723830735e-06, | |
| "loss": 0.2764, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5693950177935944, | |
| "grad_norm": 20.839887619018555, | |
| "learning_rate": 3.56347438752784e-06, | |
| "loss": 0.2067, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.604982206405694, | |
| "grad_norm": 2.853170156478882, | |
| "learning_rate": 3.78619153674833e-06, | |
| "loss": 0.243, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6405693950177936, | |
| "grad_norm": 6.61458683013916, | |
| "learning_rate": 4.00890868596882e-06, | |
| "loss": 0.1886, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.6761565836298933, | |
| "grad_norm": 3.499279022216797, | |
| "learning_rate": 4.231625835189309e-06, | |
| "loss": 0.1987, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.7117437722419929, | |
| "grad_norm": 32.111114501953125, | |
| "learning_rate": 4.4543429844098e-06, | |
| "loss": 0.2239, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7473309608540926, | |
| "grad_norm": 3.83589506149292, | |
| "learning_rate": 4.67706013363029e-06, | |
| "loss": 0.1891, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.7829181494661922, | |
| "grad_norm": 3.3233108520507812, | |
| "learning_rate": 4.89977728285078e-06, | |
| "loss": 0.1335, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.8185053380782918, | |
| "grad_norm": 19.36582374572754, | |
| "learning_rate": 5.12249443207127e-06, | |
| "loss": 0.0513, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.8540925266903915, | |
| "grad_norm": 0.7740408182144165, | |
| "learning_rate": 5.34521158129176e-06, | |
| "loss": 0.1499, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.8896797153024911, | |
| "grad_norm": 0.18774119019508362, | |
| "learning_rate": 5.5679287305122494e-06, | |
| "loss": 0.1303, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.9252669039145908, | |
| "grad_norm": 0.2991533875465393, | |
| "learning_rate": 5.7906458797327404e-06, | |
| "loss": 0.0695, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.9608540925266904, | |
| "grad_norm": 0.08448722958564758, | |
| "learning_rate": 6.01336302895323e-06, | |
| "loss": 0.1109, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.99644128113879, | |
| "grad_norm": 30.85651397705078, | |
| "learning_rate": 6.23608017817372e-06, | |
| "loss": 0.2155, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9559412550066756, | |
| "eval_f1_per_label": [ | |
| 0.9255079006772009, | |
| 0.9687203791469194 | |
| ], | |
| "eval_f1_weighted": 0.9556239404117711, | |
| "eval_loss": 0.17148031294345856, | |
| "eval_precision_per_label": [ | |
| 0.9490740740740741, | |
| 0.9587242026266416 | |
| ], | |
| "eval_precision_weighted": 0.9557995308223255, | |
| "eval_recall_per_label": [ | |
| 0.9030837004405287, | |
| 0.9789272030651341 | |
| ], | |
| "eval_recall_weighted": 0.9559412550066756, | |
| "eval_runtime": 1.3508, | |
| "eval_samples_per_second": 554.494, | |
| "eval_steps_per_second": 69.589, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 1.0320284697508897, | |
| "grad_norm": 37.36682891845703, | |
| "learning_rate": 6.458797327394209e-06, | |
| "loss": 0.2318, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.0676156583629894, | |
| "grad_norm": 3.181389093399048, | |
| "learning_rate": 6.6815144766147e-06, | |
| "loss": 0.29, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.103202846975089, | |
| "grad_norm": 0.6792677640914917, | |
| "learning_rate": 6.9042316258351895e-06, | |
| "loss": 0.0621, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.1387900355871885, | |
| "grad_norm": 31.2163143157959, | |
| "learning_rate": 7.12694877505568e-06, | |
| "loss": 0.3279, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.1743772241992882, | |
| "grad_norm": 32.702980041503906, | |
| "learning_rate": 7.349665924276171e-06, | |
| "loss": 0.0851, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.209964412811388, | |
| "grad_norm": 76.18331146240234, | |
| "learning_rate": 7.57238307349666e-06, | |
| "loss": 0.3339, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.2455516014234875, | |
| "grad_norm": 76.69121551513672, | |
| "learning_rate": 7.79510022271715e-06, | |
| "loss": 0.0757, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.281138790035587, | |
| "grad_norm": 0.06500601023435593, | |
| "learning_rate": 8.01781737193764e-06, | |
| "loss": 0.188, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.3167259786476868, | |
| "grad_norm": 95.82825469970703, | |
| "learning_rate": 8.24053452115813e-06, | |
| "loss": 0.2278, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.3523131672597866, | |
| "grad_norm": 49.43801498413086, | |
| "learning_rate": 8.463251670378619e-06, | |
| "loss": 0.2501, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.387900355871886, | |
| "grad_norm": 40.980369567871094, | |
| "learning_rate": 8.68596881959911e-06, | |
| "loss": 0.1424, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.4234875444839858, | |
| "grad_norm": 1.2029680013656616, | |
| "learning_rate": 8.9086859688196e-06, | |
| "loss": 0.1464, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.4590747330960854, | |
| "grad_norm": 26.718364715576172, | |
| "learning_rate": 9.13140311804009e-06, | |
| "loss": 0.2213, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.4946619217081851, | |
| "grad_norm": 29.254457473754883, | |
| "learning_rate": 9.35412026726058e-06, | |
| "loss": 0.1796, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.5302491103202847, | |
| "grad_norm": 0.17349238693714142, | |
| "learning_rate": 9.57683741648107e-06, | |
| "loss": 0.1021, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.5658362989323842, | |
| "grad_norm": 0.27866968512535095, | |
| "learning_rate": 9.79955456570156e-06, | |
| "loss": 0.2656, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.601423487544484, | |
| "grad_norm": 0.02428502030670643, | |
| "learning_rate": 9.985185185185185e-06, | |
| "loss": 0.0504, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.6370106761565837, | |
| "grad_norm": 0.0974503755569458, | |
| "learning_rate": 9.837037037037038e-06, | |
| "loss": 0.062, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.6725978647686834, | |
| "grad_norm": 1.3685508966445923, | |
| "learning_rate": 9.688888888888889e-06, | |
| "loss": 0.0459, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.708185053380783, | |
| "grad_norm": 1.2251461744308472, | |
| "learning_rate": 9.540740740740742e-06, | |
| "loss": 0.1173, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.7437722419928825, | |
| "grad_norm": 62.15313720703125, | |
| "learning_rate": 9.392592592592593e-06, | |
| "loss": 0.1621, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.7793594306049823, | |
| "grad_norm": 0.03026748262345791, | |
| "learning_rate": 9.244444444444445e-06, | |
| "loss": 0.1064, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.814946619217082, | |
| "grad_norm": 0.4413605332374573, | |
| "learning_rate": 9.096296296296298e-06, | |
| "loss": 0.1794, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.8505338078291815, | |
| "grad_norm": 0.08637289702892303, | |
| "learning_rate": 8.948148148148149e-06, | |
| "loss": 0.0915, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.886120996441281, | |
| "grad_norm": 0.09529650211334229, | |
| "learning_rate": 8.8e-06, | |
| "loss": 0.052, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.9217081850533808, | |
| "grad_norm": 107.46017456054688, | |
| "learning_rate": 8.651851851851852e-06, | |
| "loss": 0.1408, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.9572953736654806, | |
| "grad_norm": 26.60268211364746, | |
| "learning_rate": 8.503703703703705e-06, | |
| "loss": 0.1605, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.99288256227758, | |
| "grad_norm": 0.018591415137052536, | |
| "learning_rate": 8.355555555555556e-06, | |
| "loss": 0.0914, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9732977303070761, | |
| "eval_f1_per_label": [ | |
| 0.9541284403669725, | |
| 0.9811676082862524 | |
| ], | |
| "eval_f1_weighted": 0.9729728270877522, | |
| "eval_loss": 0.1353287547826767, | |
| "eval_precision_per_label": [ | |
| 0.9952153110047847, | |
| 0.9648148148148148 | |
| ], | |
| "eval_precision_weighted": 0.9740283163303329, | |
| "eval_recall_per_label": [ | |
| 0.9162995594713657, | |
| 0.9980842911877394 | |
| ], | |
| "eval_recall_weighted": 0.9732977303070761, | |
| "eval_runtime": 1.309, | |
| "eval_samples_per_second": 572.195, | |
| "eval_steps_per_second": 71.811, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 2.0284697508896796, | |
| "grad_norm": 0.015944845974445343, | |
| "learning_rate": 8.207407407407409e-06, | |
| "loss": 0.0011, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.0640569395017794, | |
| "grad_norm": 0.03662079572677612, | |
| "learning_rate": 8.05925925925926e-06, | |
| "loss": 0.0475, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.099644128113879, | |
| "grad_norm": 0.03478744253516197, | |
| "learning_rate": 7.911111111111112e-06, | |
| "loss": 0.0017, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.135231316725979, | |
| "grad_norm": 0.03390470892190933, | |
| "learning_rate": 7.762962962962963e-06, | |
| "loss": 0.0054, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.170818505338078, | |
| "grad_norm": 0.007953139953315258, | |
| "learning_rate": 7.614814814814816e-06, | |
| "loss": 0.0096, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.206405693950178, | |
| "grad_norm": 45.853023529052734, | |
| "learning_rate": 7.4666666666666675e-06, | |
| "loss": 0.0893, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.2419928825622777, | |
| "grad_norm": 0.03887489438056946, | |
| "learning_rate": 7.31851851851852e-06, | |
| "loss": 0.0004, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.277580071174377, | |
| "grad_norm": 0.04745912551879883, | |
| "learning_rate": 7.170370370370371e-06, | |
| "loss": 0.1963, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.3131672597864767, | |
| "grad_norm": 0.05072787404060364, | |
| "learning_rate": 7.022222222222222e-06, | |
| "loss": 0.0231, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.3487544483985765, | |
| "grad_norm": 0.026582635939121246, | |
| "learning_rate": 6.8740740740740745e-06, | |
| "loss": 0.0149, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.3843416370106763, | |
| "grad_norm": 0.014482633210718632, | |
| "learning_rate": 6.725925925925927e-06, | |
| "loss": 0.0994, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.419928825622776, | |
| "grad_norm": 0.025208059698343277, | |
| "learning_rate": 6.577777777777779e-06, | |
| "loss": 0.0006, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.4555160142348753, | |
| "grad_norm": 0.01709064655005932, | |
| "learning_rate": 6.42962962962963e-06, | |
| "loss": 0.1219, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.491103202846975, | |
| "grad_norm": 0.1339588463306427, | |
| "learning_rate": 6.2814814814814814e-06, | |
| "loss": 0.0006, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.526690391459075, | |
| "grad_norm": 24.798721313476562, | |
| "learning_rate": 6.133333333333334e-06, | |
| "loss": 0.0029, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.562277580071174, | |
| "grad_norm": 1.3540862798690796, | |
| "learning_rate": 5.985185185185186e-06, | |
| "loss": 0.081, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.597864768683274, | |
| "grad_norm": 0.04109741002321243, | |
| "learning_rate": 5.837037037037038e-06, | |
| "loss": 0.0006, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.6334519572953736, | |
| "grad_norm": 0.010597619228065014, | |
| "learning_rate": 5.688888888888889e-06, | |
| "loss": 0.013, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.6690391459074734, | |
| "grad_norm": 0.02383551187813282, | |
| "learning_rate": 5.540740740740741e-06, | |
| "loss": 0.0008, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.704626334519573, | |
| "grad_norm": 1.2794164419174194, | |
| "learning_rate": 5.392592592592593e-06, | |
| "loss": 0.1707, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.7402135231316724, | |
| "grad_norm": 0.014402506873011589, | |
| "learning_rate": 5.244444444444445e-06, | |
| "loss": 0.0864, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.775800711743772, | |
| "grad_norm": 0.013125807978212833, | |
| "learning_rate": 5.096296296296297e-06, | |
| "loss": 0.0205, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.811387900355872, | |
| "grad_norm": 0.2091672271490097, | |
| "learning_rate": 4.9481481481481485e-06, | |
| "loss": 0.0027, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.8469750889679717, | |
| "grad_norm": 0.13218224048614502, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 0.0004, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.882562277580071, | |
| "grad_norm": 2.1445350646972656, | |
| "learning_rate": 4.651851851851853e-06, | |
| "loss": 0.1045, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.9181494661921707, | |
| "grad_norm": 0.016628708690404892, | |
| "learning_rate": 4.503703703703704e-06, | |
| "loss": 0.0005, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.9537366548042705, | |
| "grad_norm": 0.04098201170563698, | |
| "learning_rate": 4.3555555555555555e-06, | |
| "loss": 0.0569, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.9893238434163703, | |
| "grad_norm": 0.7140023708343506, | |
| "learning_rate": 4.207407407407408e-06, | |
| "loss": 0.0014, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9893190921228304, | |
| "eval_f1_per_label": [ | |
| 0.9821428571428571, | |
| 0.9923809523809524 | |
| ], | |
| "eval_f1_weighted": 0.989278085065802, | |
| "eval_loss": 0.050094157457351685, | |
| "eval_precision_per_label": [ | |
| 0.995475113122172, | |
| 0.9867424242424242 | |
| ], | |
| "eval_precision_weighted": 0.9893890469069138, | |
| "eval_recall_per_label": [ | |
| 0.9691629955947136, | |
| 0.9980842911877394 | |
| ], | |
| "eval_recall_weighted": 0.9893190921228304, | |
| "eval_runtime": 1.3422, | |
| "eval_samples_per_second": 558.027, | |
| "eval_steps_per_second": 70.033, | |
| "step": 843 | |
| }, | |
| { | |
| "epoch": 3.0249110320284696, | |
| "grad_norm": 0.009055254980921745, | |
| "learning_rate": 4.05925925925926e-06, | |
| "loss": 0.124, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3.0604982206405693, | |
| "grad_norm": 0.005354477558284998, | |
| "learning_rate": 3.911111111111112e-06, | |
| "loss": 0.0008, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 3.096085409252669, | |
| "grad_norm": 0.006784161552786827, | |
| "learning_rate": 3.7629629629629633e-06, | |
| "loss": 0.0736, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 3.131672597864769, | |
| "grad_norm": 0.007448482792824507, | |
| "learning_rate": 3.614814814814815e-06, | |
| "loss": 0.0047, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 3.167259786476868, | |
| "grad_norm": 0.0065169306471943855, | |
| "learning_rate": 3.4666666666666672e-06, | |
| "loss": 0.0003, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 3.202846975088968, | |
| "grad_norm": 0.00644827401265502, | |
| "learning_rate": 3.3185185185185185e-06, | |
| "loss": 0.0007, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.2384341637010676, | |
| "grad_norm": 12.251897811889648, | |
| "learning_rate": 3.1703703703703707e-06, | |
| "loss": 0.0016, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 3.2740213523131674, | |
| "grad_norm": 0.010300640016794205, | |
| "learning_rate": 3.0222222222222225e-06, | |
| "loss": 0.0002, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 3.309608540925267, | |
| "grad_norm": 0.006541989278048277, | |
| "learning_rate": 2.874074074074074e-06, | |
| "loss": 0.0054, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 3.3451957295373664, | |
| "grad_norm": 0.08283556252717972, | |
| "learning_rate": 2.7259259259259264e-06, | |
| "loss": 0.0006, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 3.380782918149466, | |
| "grad_norm": 0.005921730771660805, | |
| "learning_rate": 2.577777777777778e-06, | |
| "loss": 0.0003, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3.416370106761566, | |
| "grad_norm": 0.004639245569705963, | |
| "learning_rate": 2.42962962962963e-06, | |
| "loss": 0.0003, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 3.4519572953736652, | |
| "grad_norm": 0.16998454928398132, | |
| "learning_rate": 2.2814814814814816e-06, | |
| "loss": 0.0007, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 3.487544483985765, | |
| "grad_norm": 0.005660816095769405, | |
| "learning_rate": 2.133333333333334e-06, | |
| "loss": 0.0241, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 3.5231316725978647, | |
| "grad_norm": 0.01572972722351551, | |
| "learning_rate": 1.985185185185185e-06, | |
| "loss": 0.0022, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 3.5587188612099645, | |
| "grad_norm": 0.01506053563207388, | |
| "learning_rate": 1.837037037037037e-06, | |
| "loss": 0.0017, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.5943060498220643, | |
| "grad_norm": 0.06420188397169113, | |
| "learning_rate": 1.688888888888889e-06, | |
| "loss": 0.0981, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 3.6298932384341636, | |
| "grad_norm": 0.050418056547641754, | |
| "learning_rate": 1.540740740740741e-06, | |
| "loss": 0.0002, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 3.6654804270462633, | |
| "grad_norm": 0.1331329494714737, | |
| "learning_rate": 1.3925925925925925e-06, | |
| "loss": 0.0002, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 3.701067615658363, | |
| "grad_norm": 0.0047861747443675995, | |
| "learning_rate": 1.2444444444444445e-06, | |
| "loss": 0.0007, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 3.7366548042704624, | |
| "grad_norm": 0.004302954766899347, | |
| "learning_rate": 1.0962962962962965e-06, | |
| "loss": 0.0002, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 3.772241992882562, | |
| "grad_norm": 0.0052270120941102505, | |
| "learning_rate": 9.481481481481482e-07, | |
| "loss": 0.0003, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 3.807829181494662, | |
| "grad_norm": 0.006781002506613731, | |
| "learning_rate": 8.000000000000001e-07, | |
| "loss": 0.0003, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 3.8434163701067616, | |
| "grad_norm": 0.006440193857997656, | |
| "learning_rate": 6.518518518518518e-07, | |
| "loss": 0.0003, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 3.8790035587188614, | |
| "grad_norm": 0.009248029440641403, | |
| "learning_rate": 5.037037037037038e-07, | |
| "loss": 0.0061, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 3.914590747330961, | |
| "grad_norm": 0.011829700320959091, | |
| "learning_rate": 3.555555555555556e-07, | |
| "loss": 0.0003, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.9501779359430604, | |
| "grad_norm": 0.024425974115729332, | |
| "learning_rate": 2.074074074074074e-07, | |
| "loss": 0.0676, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 3.98576512455516, | |
| "grad_norm": 0.00512115890160203, | |
| "learning_rate": 5.9259259259259263e-08, | |
| "loss": 0.0002, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9933244325767691, | |
| "eval_f1_per_label": [ | |
| 0.9888641425389755, | |
| 0.9952335557673975 | |
| ], | |
| "eval_f1_weighted": 0.9933031728530427, | |
| "eval_loss": 0.03607647866010666, | |
| "eval_precision_per_label": [ | |
| 1.0, | |
| 0.9905123339658444 | |
| ], | |
| "eval_precision_weighted": 0.9933877681310691, | |
| "eval_recall_per_label": [ | |
| 0.9779735682819384, | |
| 1.0 | |
| ], | |
| "eval_recall_weighted": 0.9933244325767691, | |
| "eval_runtime": 5.013, | |
| "eval_samples_per_second": 149.411, | |
| "eval_steps_per_second": 18.751, | |
| "step": 1124 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1124, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 87830786944920.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |