| { |
| "best_metric": 0.6937354988399073, |
| "best_model_checkpoint": "outputs/models/distilbert-clinical-ner/checkpoint-770", |
| "epoch": 77.0, |
| "eval_steps": 500, |
| "global_step": 770, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_f1": 0.019590382902938554, |
| "eval_loss": 4.235354900360107, |
| "eval_precision": 0.01608187134502924, |
| "eval_recall": 0.025056947608200455, |
| "eval_runtime": 0.1555, |
| "eval_samples_per_second": 128.613, |
| "eval_steps_per_second": 12.861, |
| "step": 10 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_f1": 0.023399014778325126, |
| "eval_loss": 4.040920734405518, |
| "eval_precision": 0.02546916890080429, |
| "eval_recall": 0.02164009111617312, |
| "eval_runtime": 0.1064, |
| "eval_samples_per_second": 187.984, |
| "eval_steps_per_second": 18.798, |
| "step": 20 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_f1": 0.0045045045045045045, |
| "eval_loss": 3.6175544261932373, |
| "eval_precision": 0.2, |
| "eval_recall": 0.002277904328018223, |
| "eval_runtime": 0.1035, |
| "eval_samples_per_second": 193.236, |
| "eval_steps_per_second": 19.324, |
| "step": 30 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_f1": 0.0, |
| "eval_loss": 3.0632073879241943, |
| "eval_precision": 0.0, |
| "eval_recall": 0.0, |
| "eval_runtime": 0.1056, |
| "eval_samples_per_second": 189.304, |
| "eval_steps_per_second": 18.93, |
| "step": 40 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 2.285052537918091, |
| "learning_rate": 1e-05, |
| "loss": 3.7184, |
| "step": 50 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_f1": 0.0, |
| "eval_loss": 2.6725738048553467, |
| "eval_precision": 0.0, |
| "eval_recall": 0.0, |
| "eval_runtime": 0.1038, |
| "eval_samples_per_second": 192.708, |
| "eval_steps_per_second": 19.271, |
| "step": 50 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_f1": 0.0022753128555176336, |
| "eval_loss": 2.3172459602355957, |
| "eval_precision": 1.0, |
| "eval_recall": 0.0011389521640091116, |
| "eval_runtime": 0.1056, |
| "eval_samples_per_second": 189.369, |
| "eval_steps_per_second": 18.937, |
| "step": 60 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_f1": 0.24705882352941175, |
| "eval_loss": 2.010183334350586, |
| "eval_precision": 0.34854771784232363, |
| "eval_recall": 0.19134396355353075, |
| "eval_runtime": 0.1045, |
| "eval_samples_per_second": 191.384, |
| "eval_steps_per_second": 19.138, |
| "step": 70 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_f1": 0.3578104138851802, |
| "eval_loss": 1.7770382165908813, |
| "eval_precision": 0.432258064516129, |
| "eval_recall": 0.3052391799544419, |
| "eval_runtime": 0.1043, |
| "eval_samples_per_second": 191.78, |
| "eval_steps_per_second": 19.178, |
| "step": 80 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_f1": 0.4306709265175719, |
| "eval_loss": 1.578804612159729, |
| "eval_precision": 0.49053857350800584, |
| "eval_recall": 0.3838268792710706, |
| "eval_runtime": 0.1049, |
| "eval_samples_per_second": 190.736, |
| "eval_steps_per_second": 19.074, |
| "step": 90 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 1.6135512590408325, |
| "learning_rate": 2e-05, |
| "loss": 2.0341, |
| "step": 100 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_f1": 0.5129151291512916, |
| "eval_loss": 1.4062659740447998, |
| "eval_precision": 0.5574866310160428, |
| "eval_recall": 0.47494305239179957, |
| "eval_runtime": 0.1053, |
| "eval_samples_per_second": 189.876, |
| "eval_steps_per_second": 18.988, |
| "step": 100 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_f1": 0.5652435357787132, |
| "eval_loss": 1.2971620559692383, |
| "eval_precision": 0.5987261146496815, |
| "eval_recall": 0.5353075170842825, |
| "eval_runtime": 0.1046, |
| "eval_samples_per_second": 191.215, |
| "eval_steps_per_second": 19.122, |
| "step": 110 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_f1": 0.5844155844155845, |
| "eval_loss": 1.22593092918396, |
| "eval_precision": 0.6066176470588235, |
| "eval_recall": 0.5637813211845103, |
| "eval_runtime": 0.1052, |
| "eval_samples_per_second": 190.037, |
| "eval_steps_per_second": 19.004, |
| "step": 120 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_f1": 0.6020642201834862, |
| "eval_loss": 1.1731911897659302, |
| "eval_precision": 0.6062355658198614, |
| "eval_recall": 0.5979498861047836, |
| "eval_runtime": 0.1047, |
| "eval_samples_per_second": 190.934, |
| "eval_steps_per_second": 19.093, |
| "step": 130 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_f1": 0.6093023255813953, |
| "eval_loss": 1.1392405033111572, |
| "eval_precision": 0.6223277909738717, |
| "eval_recall": 0.5968109339407744, |
| "eval_runtime": 0.1076, |
| "eval_samples_per_second": 185.839, |
| "eval_steps_per_second": 18.584, |
| "step": 140 |
| }, |
| { |
| "epoch": 15.0, |
| "grad_norm": 1.8851341009140015, |
| "learning_rate": 1.888888888888889e-05, |
| "loss": 1.0843, |
| "step": 150 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_f1": 0.6329849012775842, |
| "eval_loss": 1.1109048128128052, |
| "eval_precision": 0.6457345971563981, |
| "eval_recall": 0.6207289293849658, |
| "eval_runtime": 0.1045, |
| "eval_samples_per_second": 191.342, |
| "eval_steps_per_second": 19.134, |
| "step": 150 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_f1": 0.6323103647944412, |
| "eval_loss": 1.111675500869751, |
| "eval_precision": 0.6431095406360424, |
| "eval_recall": 0.621867881548975, |
| "eval_runtime": 0.1064, |
| "eval_samples_per_second": 187.947, |
| "eval_steps_per_second": 18.795, |
| "step": 160 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_f1": 0.6406976744186046, |
| "eval_loss": 1.1105479001998901, |
| "eval_precision": 0.6543942992874109, |
| "eval_recall": 0.6275626423690205, |
| "eval_runtime": 0.1038, |
| "eval_samples_per_second": 192.723, |
| "eval_steps_per_second": 19.272, |
| "step": 170 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_f1": 0.6418338108882521, |
| "eval_loss": 1.1081936359405518, |
| "eval_precision": 0.6459054209919262, |
| "eval_recall": 0.6378132118451025, |
| "eval_runtime": 0.1093, |
| "eval_samples_per_second": 182.962, |
| "eval_steps_per_second": 18.296, |
| "step": 180 |
| }, |
| { |
| "epoch": 19.0, |
| "eval_f1": 0.656629994209612, |
| "eval_loss": 1.0905473232269287, |
| "eval_precision": 0.6678445229681979, |
| "eval_recall": 0.6457858769931663, |
| "eval_runtime": 0.1058, |
| "eval_samples_per_second": 189.016, |
| "eval_steps_per_second": 18.902, |
| "step": 190 |
| }, |
| { |
| "epoch": 20.0, |
| "grad_norm": 2.453874111175537, |
| "learning_rate": 1.7777777777777777e-05, |
| "loss": 0.6709, |
| "step": 200 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_f1": 0.6527536231884057, |
| "eval_loss": 1.0979650020599365, |
| "eval_precision": 0.6646989374262101, |
| "eval_recall": 0.6412300683371298, |
| "eval_runtime": 0.1051, |
| "eval_samples_per_second": 190.38, |
| "eval_steps_per_second": 19.038, |
| "step": 200 |
| }, |
| { |
| "epoch": 21.0, |
| "eval_f1": 0.660889659156557, |
| "eval_loss": 1.1073075532913208, |
| "eval_precision": 0.6705744431418523, |
| "eval_recall": 0.6514806378132119, |
| "eval_runtime": 0.1063, |
| "eval_samples_per_second": 188.158, |
| "eval_steps_per_second": 18.816, |
| "step": 210 |
| }, |
| { |
| "epoch": 22.0, |
| "eval_f1": 0.6520231213872832, |
| "eval_loss": 1.109878420829773, |
| "eval_precision": 0.6619718309859155, |
| "eval_recall": 0.642369020501139, |
| "eval_runtime": 0.1108, |
| "eval_samples_per_second": 180.582, |
| "eval_steps_per_second": 18.058, |
| "step": 220 |
| }, |
| { |
| "epoch": 23.0, |
| "eval_f1": 0.6666666666666666, |
| "eval_loss": 1.1079308986663818, |
| "eval_precision": 0.6838323353293413, |
| "eval_recall": 0.6503416856492027, |
| "eval_runtime": 0.1051, |
| "eval_samples_per_second": 190.371, |
| "eval_steps_per_second": 19.037, |
| "step": 230 |
| }, |
| { |
| "epoch": 24.0, |
| "eval_f1": 0.6685714285714285, |
| "eval_loss": 1.0995490550994873, |
| "eval_precision": 0.6708715596330275, |
| "eval_recall": 0.6662870159453302, |
| "eval_runtime": 0.1076, |
| "eval_samples_per_second": 185.917, |
| "eval_steps_per_second": 18.592, |
| "step": 240 |
| }, |
| { |
| "epoch": 25.0, |
| "grad_norm": 1.9804632663726807, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 0.4563, |
| "step": 250 |
| }, |
| { |
| "epoch": 25.0, |
| "eval_f1": 0.6623831775700935, |
| "eval_loss": 1.1412475109100342, |
| "eval_precision": 0.6798561151079137, |
| "eval_recall": 0.6457858769931663, |
| "eval_runtime": 0.1043, |
| "eval_samples_per_second": 191.672, |
| "eval_steps_per_second": 19.167, |
| "step": 250 |
| }, |
| { |
| "epoch": 26.0, |
| "eval_f1": 0.6685878962536023, |
| "eval_loss": 1.1206316947937012, |
| "eval_precision": 0.676779463243874, |
| "eval_recall": 0.6605922551252847, |
| "eval_runtime": 0.1025, |
| "eval_samples_per_second": 195.213, |
| "eval_steps_per_second": 19.521, |
| "step": 260 |
| }, |
| { |
| "epoch": 27.0, |
| "eval_f1": 0.674013921113689, |
| "eval_loss": 1.1223537921905518, |
| "eval_precision": 0.6867612293144209, |
| "eval_recall": 0.6617312072892938, |
| "eval_runtime": 0.1023, |
| "eval_samples_per_second": 195.488, |
| "eval_steps_per_second": 19.549, |
| "step": 270 |
| }, |
| { |
| "epoch": 28.0, |
| "eval_f1": 0.6787595084844938, |
| "eval_loss": 1.1268706321716309, |
| "eval_precision": 0.6979542719614922, |
| "eval_recall": 0.6605922551252847, |
| "eval_runtime": 0.107, |
| "eval_samples_per_second": 186.844, |
| "eval_steps_per_second": 18.684, |
| "step": 280 |
| }, |
| { |
| "epoch": 29.0, |
| "eval_f1": 0.6817391304347827, |
| "eval_loss": 1.143689751625061, |
| "eval_precision": 0.6942148760330579, |
| "eval_recall": 0.6697038724373576, |
| "eval_runtime": 0.1048, |
| "eval_samples_per_second": 190.916, |
| "eval_steps_per_second": 19.092, |
| "step": 290 |
| }, |
| { |
| "epoch": 30.0, |
| "grad_norm": 1.2570631504058838, |
| "learning_rate": 1.555555555555556e-05, |
| "loss": 0.3229, |
| "step": 300 |
| }, |
| { |
| "epoch": 30.0, |
| "eval_f1": 0.6781807714450201, |
| "eval_loss": 1.1411770582199097, |
| "eval_precision": 0.6856810244470314, |
| "eval_recall": 0.6708428246013668, |
| "eval_runtime": 0.1118, |
| "eval_samples_per_second": 178.865, |
| "eval_steps_per_second": 17.887, |
| "step": 300 |
| }, |
| { |
| "epoch": 31.0, |
| "eval_f1": 0.6797235023041475, |
| "eval_loss": 1.1665282249450684, |
| "eval_precision": 0.6876456876456877, |
| "eval_recall": 0.6719817767653758, |
| "eval_runtime": 0.1061, |
| "eval_samples_per_second": 188.516, |
| "eval_steps_per_second": 18.852, |
| "step": 310 |
| }, |
| { |
| "epoch": 32.0, |
| "eval_f1": 0.6785714285714286, |
| "eval_loss": 1.147858738899231, |
| "eval_precision": 0.6864801864801865, |
| "eval_recall": 0.6708428246013668, |
| "eval_runtime": 0.1079, |
| "eval_samples_per_second": 185.36, |
| "eval_steps_per_second": 18.536, |
| "step": 320 |
| }, |
| { |
| "epoch": 33.0, |
| "eval_f1": 0.6774193548387096, |
| "eval_loss": 1.1554282903671265, |
| "eval_precision": 0.6853146853146853, |
| "eval_recall": 0.6697038724373576, |
| "eval_runtime": 0.1037, |
| "eval_samples_per_second": 192.925, |
| "eval_steps_per_second": 19.292, |
| "step": 330 |
| }, |
| { |
| "epoch": 34.0, |
| "eval_f1": 0.6797687861271676, |
| "eval_loss": 1.15742027759552, |
| "eval_precision": 0.6901408450704225, |
| "eval_recall": 0.6697038724373576, |
| "eval_runtime": 0.1053, |
| "eval_samples_per_second": 189.904, |
| "eval_steps_per_second": 18.99, |
| "step": 340 |
| }, |
| { |
| "epoch": 35.0, |
| "grad_norm": 1.0945429801940918, |
| "learning_rate": 1.4444444444444446e-05, |
| "loss": 0.2396, |
| "step": 350 |
| }, |
| { |
| "epoch": 35.0, |
| "eval_f1": 0.6797235023041475, |
| "eval_loss": 1.1754865646362305, |
| "eval_precision": 0.6876456876456877, |
| "eval_recall": 0.6719817767653758, |
| "eval_runtime": 0.1057, |
| "eval_samples_per_second": 189.199, |
| "eval_steps_per_second": 18.92, |
| "step": 350 |
| }, |
| { |
| "epoch": 36.0, |
| "eval_f1": 0.6735870818915801, |
| "eval_loss": 1.1885067224502563, |
| "eval_precision": 0.6822429906542056, |
| "eval_recall": 0.6651480637813212, |
| "eval_runtime": 0.1, |
| "eval_samples_per_second": 200.0, |
| "eval_steps_per_second": 20.0, |
| "step": 360 |
| }, |
| { |
| "epoch": 37.0, |
| "eval_f1": 0.6806526806526807, |
| "eval_loss": 1.181584119796753, |
| "eval_precision": 0.6968973747016707, |
| "eval_recall": 0.6651480637813212, |
| "eval_runtime": 0.1076, |
| "eval_samples_per_second": 185.858, |
| "eval_steps_per_second": 18.586, |
| "step": 370 |
| }, |
| { |
| "epoch": 38.0, |
| "eval_f1": 0.6787172011661807, |
| "eval_loss": 1.1876161098480225, |
| "eval_precision": 0.6953405017921147, |
| "eval_recall": 0.662870159453303, |
| "eval_runtime": 0.1161, |
| "eval_samples_per_second": 172.269, |
| "eval_steps_per_second": 17.227, |
| "step": 380 |
| }, |
| { |
| "epoch": 39.0, |
| "eval_f1": 0.6818713450292397, |
| "eval_loss": 1.2116471529006958, |
| "eval_precision": 0.7007211538461539, |
| "eval_recall": 0.664009111617312, |
| "eval_runtime": 0.1027, |
| "eval_samples_per_second": 194.71, |
| "eval_steps_per_second": 19.471, |
| "step": 390 |
| }, |
| { |
| "epoch": 40.0, |
| "grad_norm": 0.8599975109100342, |
| "learning_rate": 1.3333333333333333e-05, |
| "loss": 0.1848, |
| "step": 400 |
| }, |
| { |
| "epoch": 40.0, |
| "eval_f1": 0.6786542923433874, |
| "eval_loss": 1.1997044086456299, |
| "eval_precision": 0.6914893617021277, |
| "eval_recall": 0.6662870159453302, |
| "eval_runtime": 0.1098, |
| "eval_samples_per_second": 182.124, |
| "eval_steps_per_second": 18.212, |
| "step": 400 |
| }, |
| { |
| "epoch": 41.0, |
| "eval_f1": 0.6817917393833625, |
| "eval_loss": 1.2281190156936646, |
| "eval_precision": 0.6967895362663495, |
| "eval_recall": 0.6674259681093394, |
| "eval_runtime": 0.1026, |
| "eval_samples_per_second": 195.027, |
| "eval_steps_per_second": 19.503, |
| "step": 410 |
| }, |
| { |
| "epoch": 42.0, |
| "eval_f1": 0.6820542412002308, |
| "eval_loss": 1.205224633216858, |
| "eval_precision": 0.6912280701754386, |
| "eval_recall": 0.673120728929385, |
| "eval_runtime": 0.1029, |
| "eval_samples_per_second": 194.454, |
| "eval_steps_per_second": 19.445, |
| "step": 420 |
| }, |
| { |
| "epoch": 43.0, |
| "eval_f1": 0.6834112149532711, |
| "eval_loss": 1.2441879510879517, |
| "eval_precision": 0.7014388489208633, |
| "eval_recall": 0.6662870159453302, |
| "eval_runtime": 0.1013, |
| "eval_samples_per_second": 197.51, |
| "eval_steps_per_second": 19.751, |
| "step": 430 |
| }, |
| { |
| "epoch": 44.0, |
| "eval_f1": 0.6762672811059909, |
| "eval_loss": 1.2410287857055664, |
| "eval_precision": 0.6841491841491841, |
| "eval_recall": 0.6685649202733486, |
| "eval_runtime": 0.1039, |
| "eval_samples_per_second": 192.454, |
| "eval_steps_per_second": 19.245, |
| "step": 440 |
| }, |
| { |
| "epoch": 45.0, |
| "grad_norm": 0.8666434288024902, |
| "learning_rate": 1.2222222222222224e-05, |
| "loss": 0.1472, |
| "step": 450 |
| }, |
| { |
| "epoch": 45.0, |
| "eval_f1": 0.6809744779582366, |
| "eval_loss": 1.2373775243759155, |
| "eval_precision": 0.693853427895981, |
| "eval_recall": 0.6685649202733486, |
| "eval_runtime": 0.1016, |
| "eval_samples_per_second": 196.912, |
| "eval_steps_per_second": 19.691, |
| "step": 450 |
| }, |
| { |
| "epoch": 46.0, |
| "eval_f1": 0.6786961583236321, |
| "eval_loss": 1.237067461013794, |
| "eval_precision": 0.694047619047619, |
| "eval_recall": 0.664009111617312, |
| "eval_runtime": 0.1002, |
| "eval_samples_per_second": 199.663, |
| "eval_steps_per_second": 19.966, |
| "step": 460 |
| }, |
| { |
| "epoch": 47.0, |
| "eval_f1": 0.6889016676250718, |
| "eval_loss": 1.2270065546035767, |
| "eval_precision": 0.6957026713124274, |
| "eval_recall": 0.6822323462414579, |
| "eval_runtime": 0.1051, |
| "eval_samples_per_second": 190.295, |
| "eval_steps_per_second": 19.03, |
| "step": 470 |
| }, |
| { |
| "epoch": 48.0, |
| "eval_f1": 0.6805555555555555, |
| "eval_loss": 1.238765001296997, |
| "eval_precision": 0.691764705882353, |
| "eval_recall": 0.6697038724373576, |
| "eval_runtime": 0.1066, |
| "eval_samples_per_second": 187.677, |
| "eval_steps_per_second": 18.768, |
| "step": 480 |
| }, |
| { |
| "epoch": 49.0, |
| "eval_f1": 0.6790914385556202, |
| "eval_loss": 1.2525634765625, |
| "eval_precision": 0.6948748510131109, |
| "eval_recall": 0.664009111617312, |
| "eval_runtime": 0.1021, |
| "eval_samples_per_second": 195.942, |
| "eval_steps_per_second": 19.594, |
| "step": 490 |
| }, |
| { |
| "epoch": 50.0, |
| "grad_norm": 0.8096102476119995, |
| "learning_rate": 1.1111111111111113e-05, |
| "loss": 0.1184, |
| "step": 500 |
| }, |
| { |
| "epoch": 50.0, |
| "eval_f1": 0.681421083284799, |
| "eval_loss": 1.2390888929367065, |
| "eval_precision": 0.6972586412395709, |
| "eval_recall": 0.6662870159453302, |
| "eval_runtime": 0.1042, |
| "eval_samples_per_second": 191.926, |
| "eval_steps_per_second": 19.193, |
| "step": 500 |
| }, |
| { |
| "epoch": 51.0, |
| "eval_f1": 0.6782810685249709, |
| "eval_loss": 1.2617552280426025, |
| "eval_precision": 0.6919431279620853, |
| "eval_recall": 0.6651480637813212, |
| "eval_runtime": 0.1011, |
| "eval_samples_per_second": 197.736, |
| "eval_steps_per_second": 19.774, |
| "step": 510 |
| }, |
| { |
| "epoch": 52.0, |
| "eval_f1": 0.6814469078179697, |
| "eval_loss": 1.2573115825653076, |
| "eval_precision": 0.6985645933014354, |
| "eval_recall": 0.6651480637813212, |
| "eval_runtime": 0.1033, |
| "eval_samples_per_second": 193.643, |
| "eval_steps_per_second": 19.364, |
| "step": 520 |
| }, |
| { |
| "epoch": 53.0, |
| "eval_f1": 0.681369704004643, |
| "eval_loss": 1.2631280422210693, |
| "eval_precision": 0.6946745562130178, |
| "eval_recall": 0.6685649202733486, |
| "eval_runtime": 0.1027, |
| "eval_samples_per_second": 194.742, |
| "eval_steps_per_second": 19.474, |
| "step": 530 |
| }, |
| { |
| "epoch": 54.0, |
| "eval_f1": 0.6822429906542057, |
| "eval_loss": 1.2612630128860474, |
| "eval_precision": 0.7002398081534772, |
| "eval_recall": 0.6651480637813212, |
| "eval_runtime": 0.1034, |
| "eval_samples_per_second": 193.355, |
| "eval_steps_per_second": 19.335, |
| "step": 540 |
| }, |
| { |
| "epoch": 55.0, |
| "grad_norm": 1.258770227432251, |
| "learning_rate": 1e-05, |
| "loss": 0.0965, |
| "step": 550 |
| }, |
| { |
| "epoch": 55.0, |
| "eval_f1": 0.678592036930179, |
| "eval_loss": 1.2565994262695312, |
| "eval_precision": 0.6877192982456141, |
| "eval_recall": 0.6697038724373576, |
| "eval_runtime": 0.1065, |
| "eval_samples_per_second": 187.769, |
| "eval_steps_per_second": 18.777, |
| "step": 550 |
| }, |
| { |
| "epoch": 56.0, |
| "eval_f1": 0.6720461095100864, |
| "eval_loss": 1.286030888557434, |
| "eval_precision": 0.6802800466744457, |
| "eval_recall": 0.664009111617312, |
| "eval_runtime": 0.1017, |
| "eval_samples_per_second": 196.637, |
| "eval_steps_per_second": 19.664, |
| "step": 560 |
| }, |
| { |
| "epoch": 57.0, |
| "eval_f1": 0.6774941995359629, |
| "eval_loss": 1.2746167182922363, |
| "eval_precision": 0.6903073286052009, |
| "eval_recall": 0.6651480637813212, |
| "eval_runtime": 0.104, |
| "eval_samples_per_second": 192.291, |
| "eval_steps_per_second": 19.229, |
| "step": 570 |
| }, |
| { |
| "epoch": 58.0, |
| "eval_f1": 0.6813441483198146, |
| "eval_loss": 1.2719839811325073, |
| "eval_precision": 0.6933962264150944, |
| "eval_recall": 0.6697038724373576, |
| "eval_runtime": 0.1009, |
| "eval_samples_per_second": 198.12, |
| "eval_steps_per_second": 19.812, |
| "step": 580 |
| }, |
| { |
| "epoch": 59.0, |
| "eval_f1": 0.6845168800931315, |
| "eval_loss": 1.2790720462799072, |
| "eval_precision": 0.7, |
| "eval_recall": 0.6697038724373576, |
| "eval_runtime": 0.1025, |
| "eval_samples_per_second": 195.09, |
| "eval_steps_per_second": 19.509, |
| "step": 590 |
| }, |
| { |
| "epoch": 60.0, |
| "grad_norm": 0.6421855688095093, |
| "learning_rate": 8.888888888888888e-06, |
| "loss": 0.0841, |
| "step": 600 |
| }, |
| { |
| "epoch": 60.0, |
| "eval_f1": 0.6827309236947792, |
| "eval_loss": 1.2661317586898804, |
| "eval_precision": 0.6878612716763006, |
| "eval_recall": 0.6776765375854215, |
| "eval_runtime": 0.1054, |
| "eval_samples_per_second": 189.834, |
| "eval_steps_per_second": 18.983, |
| "step": 600 |
| }, |
| { |
| "epoch": 61.0, |
| "eval_f1": 0.6803039158386909, |
| "eval_loss": 1.2873255014419556, |
| "eval_precision": 0.6986794717887155, |
| "eval_recall": 0.662870159453303, |
| "eval_runtime": 0.1028, |
| "eval_samples_per_second": 194.643, |
| "eval_steps_per_second": 19.464, |
| "step": 610 |
| }, |
| { |
| "epoch": 62.0, |
| "eval_f1": 0.6809248554913295, |
| "eval_loss": 1.2766045331954956, |
| "eval_precision": 0.6913145539906104, |
| "eval_recall": 0.6708428246013668, |
| "eval_runtime": 0.1044, |
| "eval_samples_per_second": 191.487, |
| "eval_steps_per_second": 19.149, |
| "step": 620 |
| }, |
| { |
| "epoch": 63.0, |
| "eval_f1": 0.6755658734764944, |
| "eval_loss": 1.2915081977844238, |
| "eval_precision": 0.6887573964497041, |
| "eval_recall": 0.662870159453303, |
| "eval_runtime": 0.1078, |
| "eval_samples_per_second": 185.542, |
| "eval_steps_per_second": 18.554, |
| "step": 630 |
| }, |
| { |
| "epoch": 64.0, |
| "eval_f1": 0.6732101616628174, |
| "eval_loss": 1.2793446779251099, |
| "eval_precision": 0.6826697892271663, |
| "eval_recall": 0.664009111617312, |
| "eval_runtime": 0.1016, |
| "eval_samples_per_second": 196.942, |
| "eval_steps_per_second": 19.694, |
| "step": 640 |
| }, |
| { |
| "epoch": 65.0, |
| "grad_norm": 0.5916463136672974, |
| "learning_rate": 7.77777777777778e-06, |
| "loss": 0.0714, |
| "step": 650 |
| }, |
| { |
| "epoch": 65.0, |
| "eval_f1": 0.6820276497695852, |
| "eval_loss": 1.3019025325775146, |
| "eval_precision": 0.6899766899766899, |
| "eval_recall": 0.6742596810933941, |
| "eval_runtime": 0.1008, |
| "eval_samples_per_second": 198.393, |
| "eval_steps_per_second": 19.839, |
| "step": 650 |
| }, |
| { |
| "epoch": 66.0, |
| "eval_f1": 0.6853473438412142, |
| "eval_loss": 1.2911741733551025, |
| "eval_precision": 0.7029940119760479, |
| "eval_recall": 0.6685649202733486, |
| "eval_runtime": 0.106, |
| "eval_samples_per_second": 188.757, |
| "eval_steps_per_second": 18.876, |
| "step": 660 |
| }, |
| { |
| "epoch": 67.0, |
| "eval_f1": 0.67816091954023, |
| "eval_loss": 1.2967917919158936, |
| "eval_precision": 0.6844547563805105, |
| "eval_recall": 0.6719817767653758, |
| "eval_runtime": 0.1092, |
| "eval_samples_per_second": 183.175, |
| "eval_steps_per_second": 18.318, |
| "step": 670 |
| }, |
| { |
| "epoch": 68.0, |
| "eval_f1": 0.6895348837209303, |
| "eval_loss": 1.2946228981018066, |
| "eval_precision": 0.7042755344418052, |
| "eval_recall": 0.6753986332574032, |
| "eval_runtime": 0.1052, |
| "eval_samples_per_second": 190.167, |
| "eval_steps_per_second": 19.017, |
| "step": 680 |
| }, |
| { |
| "epoch": 69.0, |
| "eval_f1": 0.6863425925925927, |
| "eval_loss": 1.2976857423782349, |
| "eval_precision": 0.6976470588235294, |
| "eval_recall": 0.6753986332574032, |
| "eval_runtime": 0.103, |
| "eval_samples_per_second": 194.22, |
| "eval_steps_per_second": 19.422, |
| "step": 690 |
| }, |
| { |
| "epoch": 70.0, |
| "grad_norm": 0.7995481491088867, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": 0.064, |
| "step": 700 |
| }, |
| { |
| "epoch": 70.0, |
| "eval_f1": 0.6771014492753623, |
| "eval_loss": 1.295568585395813, |
| "eval_precision": 0.6894923258559622, |
| "eval_recall": 0.6651480637813212, |
| "eval_runtime": 0.1031, |
| "eval_samples_per_second": 193.92, |
| "eval_steps_per_second": 19.392, |
| "step": 700 |
| }, |
| { |
| "epoch": 71.0, |
| "eval_f1": 0.6797687861271676, |
| "eval_loss": 1.2898850440979004, |
| "eval_precision": 0.6901408450704225, |
| "eval_recall": 0.6697038724373576, |
| "eval_runtime": 0.1005, |
| "eval_samples_per_second": 198.942, |
| "eval_steps_per_second": 19.894, |
| "step": 710 |
| }, |
| { |
| "epoch": 72.0, |
| "eval_f1": 0.6806526806526807, |
| "eval_loss": 1.3075172901153564, |
| "eval_precision": 0.6968973747016707, |
| "eval_recall": 0.6651480637813212, |
| "eval_runtime": 0.1087, |
| "eval_samples_per_second": 184.017, |
| "eval_steps_per_second": 18.402, |
| "step": 720 |
| }, |
| { |
| "epoch": 73.0, |
| "eval_f1": 0.683750728013978, |
| "eval_loss": 1.2973222732543945, |
| "eval_precision": 0.699642431466031, |
| "eval_recall": 0.6685649202733486, |
| "eval_runtime": 0.1054, |
| "eval_samples_per_second": 189.672, |
| "eval_steps_per_second": 18.967, |
| "step": 730 |
| }, |
| { |
| "epoch": 74.0, |
| "eval_f1": 0.6872812135355894, |
| "eval_loss": 1.3102946281433105, |
| "eval_precision": 0.7045454545454546, |
| "eval_recall": 0.6708428246013668, |
| "eval_runtime": 0.1064, |
| "eval_samples_per_second": 188.0, |
| "eval_steps_per_second": 18.8, |
| "step": 740 |
| }, |
| { |
| "epoch": 75.0, |
| "grad_norm": 0.8353786468505859, |
| "learning_rate": 5.555555555555557e-06, |
| "loss": 0.0575, |
| "step": 750 |
| }, |
| { |
| "epoch": 75.0, |
| "eval_f1": 0.6797915460335843, |
| "eval_loss": 1.3147099018096924, |
| "eval_precision": 0.6914016489988222, |
| "eval_recall": 0.6685649202733486, |
| "eval_runtime": 0.1049, |
| "eval_samples_per_second": 190.589, |
| "eval_steps_per_second": 19.059, |
| "step": 750 |
| }, |
| { |
| "epoch": 76.0, |
| "eval_f1": 0.6845168800931315, |
| "eval_loss": 1.3087732791900635, |
| "eval_precision": 0.7, |
| "eval_recall": 0.6697038724373576, |
| "eval_runtime": 0.105, |
| "eval_samples_per_second": 190.4, |
| "eval_steps_per_second": 19.04, |
| "step": 760 |
| }, |
| { |
| "epoch": 77.0, |
| "eval_f1": 0.6937354988399073, |
| "eval_loss": 1.3092721700668335, |
| "eval_precision": 0.706855791962175, |
| "eval_recall": 0.6810933940774487, |
| "eval_runtime": 0.1053, |
| "eval_samples_per_second": 189.996, |
| "eval_steps_per_second": 19.0, |
| "step": 770 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 100, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 402935426826240.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
