|
{ |
|
"best_metric": 0.04516952857375145, |
|
"best_model_checkpoint": "./models/results_short_jokes_47/checkpoint-3400", |
|
"epoch": 0.6262086748319367, |
|
"global_step": 3400, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 8.000000000000001e-07, |
|
"loss": 0.691, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 1.6000000000000001e-06, |
|
"loss": 0.6954, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 2.4000000000000003e-06, |
|
"loss": 0.6964, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 3.2000000000000003e-06, |
|
"loss": 0.6855, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 4.000000000000001e-06, |
|
"loss": 0.6916, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 4.800000000000001e-06, |
|
"loss": 0.6845, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 5.600000000000001e-06, |
|
"loss": 0.6708, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 6.4000000000000006e-06, |
|
"loss": 0.6411, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 7.2e-06, |
|
"loss": 0.5579, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 7.9e-06, |
|
"loss": 0.3916, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 8.7e-06, |
|
"loss": 0.262, |
|
"step": 88 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 9.5e-06, |
|
"loss": 0.2353, |
|
"step": 96 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"eval_accuracy": 0.9376661947024899, |
|
"eval_f1": 0.9405800441123219, |
|
"eval_loss": 0.1874532550573349, |
|
"eval_precision": 0.9014102280972963, |
|
"eval_recall": 0.9833086691674984, |
|
"eval_runtime": 312.5596, |
|
"eval_samples_per_second": 185.289, |
|
"eval_steps_per_second": 23.164, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 1.03e-05, |
|
"loss": 0.193, |
|
"step": 104 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 1.11e-05, |
|
"loss": 0.1671, |
|
"step": 112 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 1.19e-05, |
|
"loss": 0.1242, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 1.2600000000000001e-05, |
|
"loss": 0.1497, |
|
"step": 128 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 1.3400000000000002e-05, |
|
"loss": 0.1173, |
|
"step": 136 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 1.42e-05, |
|
"loss": 0.1598, |
|
"step": 144 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 1.5e-05, |
|
"loss": 0.1312, |
|
"step": 152 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 1.58e-05, |
|
"loss": 0.1374, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 1.66e-05, |
|
"loss": 0.1055, |
|
"step": 168 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 1.74e-05, |
|
"loss": 0.1114, |
|
"step": 176 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 1.8200000000000002e-05, |
|
"loss": 0.1404, |
|
"step": 184 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 1.9e-05, |
|
"loss": 0.1289, |
|
"step": 192 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 1.9800000000000004e-05, |
|
"loss": 0.136, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"eval_accuracy": 0.962185309251649, |
|
"eval_f1": 0.9613947257086447, |
|
"eval_loss": 0.11203108727931976, |
|
"eval_precision": 0.9854721549636803, |
|
"eval_recall": 0.9384657741680146, |
|
"eval_runtime": 315.0228, |
|
"eval_samples_per_second": 183.841, |
|
"eval_steps_per_second": 22.982, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 2.06e-05, |
|
"loss": 0.1112, |
|
"step": 208 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 2.1400000000000002e-05, |
|
"loss": 0.1447, |
|
"step": 216 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 2.22e-05, |
|
"loss": 0.143, |
|
"step": 224 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 2.3000000000000003e-05, |
|
"loss": 0.1175, |
|
"step": 232 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 2.38e-05, |
|
"loss": 0.1208, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 2.46e-05, |
|
"loss": 0.1563, |
|
"step": 248 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 2.54e-05, |
|
"loss": 0.0701, |
|
"step": 256 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 2.6200000000000003e-05, |
|
"loss": 0.0881, |
|
"step": 264 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 2.7000000000000002e-05, |
|
"loss": 0.1091, |
|
"step": 272 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 2.7800000000000005e-05, |
|
"loss": 0.1512, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 2.86e-05, |
|
"loss": 0.0802, |
|
"step": 288 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 2.94e-05, |
|
"loss": 0.103, |
|
"step": 296 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"eval_accuracy": 0.9501674897261456, |
|
"eval_f1": 0.9481028591979861, |
|
"eval_loss": 0.13948623836040497, |
|
"eval_precision": 0.992806839151885, |
|
"eval_recall": 0.9072512647554806, |
|
"eval_runtime": 304.8107, |
|
"eval_samples_per_second": 190.0, |
|
"eval_steps_per_second": 23.752, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 3.02e-05, |
|
"loss": 0.0864, |
|
"step": 304 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 3.1e-05, |
|
"loss": 0.0991, |
|
"step": 312 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 3.18e-05, |
|
"loss": 0.0577, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 3.26e-05, |
|
"loss": 0.1446, |
|
"step": 328 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 3.3400000000000005e-05, |
|
"loss": 0.1009, |
|
"step": 336 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 3.4200000000000005e-05, |
|
"loss": 0.1059, |
|
"step": 344 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 3.5e-05, |
|
"loss": 0.1156, |
|
"step": 352 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 3.58e-05, |
|
"loss": 0.0714, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 3.66e-05, |
|
"loss": 0.0862, |
|
"step": 368 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 3.74e-05, |
|
"loss": 0.1634, |
|
"step": 376 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 3.82e-05, |
|
"loss": 0.0953, |
|
"step": 384 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 3.9000000000000006e-05, |
|
"loss": 0.0822, |
|
"step": 392 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 3.9800000000000005e-05, |
|
"loss": 0.0768, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"eval_accuracy": 0.973028973995925, |
|
"eval_f1": 0.9733447098976109, |
|
"eval_loss": 0.08835102617740631, |
|
"eval_precision": 0.9653386589039705, |
|
"eval_recall": 0.9814846680662147, |
|
"eval_runtime": 320.6331, |
|
"eval_samples_per_second": 180.624, |
|
"eval_steps_per_second": 22.58, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 4.0600000000000004e-05, |
|
"loss": 0.1154, |
|
"step": 408 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 4.14e-05, |
|
"loss": 0.1243, |
|
"step": 416 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 4.22e-05, |
|
"loss": 0.0727, |
|
"step": 424 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 4.3e-05, |
|
"loss": 0.0955, |
|
"step": 432 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 4.38e-05, |
|
"loss": 0.0822, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 4.46e-05, |
|
"loss": 0.1043, |
|
"step": 448 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 4.5400000000000006e-05, |
|
"loss": 0.1473, |
|
"step": 456 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 4.6200000000000005e-05, |
|
"loss": 0.0848, |
|
"step": 464 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 4.7e-05, |
|
"loss": 0.139, |
|
"step": 472 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 4.78e-05, |
|
"loss": 0.103, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 4.86e-05, |
|
"loss": 0.1075, |
|
"step": 488 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 4.94e-05, |
|
"loss": 0.1285, |
|
"step": 496 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"eval_accuracy": 0.9650861622405636, |
|
"eval_f1": 0.9643335920412051, |
|
"eval_loss": 0.10335744917392731, |
|
"eval_precision": 0.9891442011941378, |
|
"eval_recall": 0.9407371717658396, |
|
"eval_runtime": 317.7591, |
|
"eval_samples_per_second": 182.258, |
|
"eval_steps_per_second": 22.785, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 4.997971190910936e-05, |
|
"loss": 0.085, |
|
"step": 504 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 4.989855954554677e-05, |
|
"loss": 0.1381, |
|
"step": 512 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 4.9817407181984176e-05, |
|
"loss": 0.1202, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 4.973625481842159e-05, |
|
"loss": 0.0778, |
|
"step": 528 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 4.9655102454859e-05, |
|
"loss": 0.0872, |
|
"step": 536 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 4.957395009129641e-05, |
|
"loss": 0.1364, |
|
"step": 544 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 4.9492797727733825e-05, |
|
"loss": 0.1305, |
|
"step": 552 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 4.9411645364171234e-05, |
|
"loss": 0.0677, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 4.933049300060865e-05, |
|
"loss": 0.1187, |
|
"step": 568 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 4.924934063704605e-05, |
|
"loss": 0.1605, |
|
"step": 576 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 4.916818827348347e-05, |
|
"loss": 0.1732, |
|
"step": 584 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 4.908703590992088e-05, |
|
"loss": 0.104, |
|
"step": 592 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 4.900588354635829e-05, |
|
"loss": 0.0872, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"eval_accuracy": 0.973305245709155, |
|
"eval_f1": 0.9731382701462973, |
|
"eval_loss": 0.081203892827034, |
|
"eval_precision": 0.982699933326315, |
|
"eval_recall": 0.9637608837801562, |
|
"eval_runtime": 323.1202, |
|
"eval_samples_per_second": 179.234, |
|
"eval_steps_per_second": 22.407, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 4.89247311827957e-05, |
|
"loss": 0.0921, |
|
"step": 608 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 4.884357881923311e-05, |
|
"loss": 0.069, |
|
"step": 616 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 4.8762426455670526e-05, |
|
"loss": 0.0517, |
|
"step": 624 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 4.8681274092107935e-05, |
|
"loss": 0.1178, |
|
"step": 632 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 4.8600121728545343e-05, |
|
"loss": 0.154, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 4.851896936498276e-05, |
|
"loss": 0.0999, |
|
"step": 648 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 4.843781700142017e-05, |
|
"loss": 0.0949, |
|
"step": 656 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 4.835666463785758e-05, |
|
"loss": 0.0821, |
|
"step": 664 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 4.827551227429499e-05, |
|
"loss": 0.0947, |
|
"step": 672 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 4.81943599107324e-05, |
|
"loss": 0.1451, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 4.811320754716982e-05, |
|
"loss": 0.084, |
|
"step": 688 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 4.8032055183607226e-05, |
|
"loss": 0.0659, |
|
"step": 696 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"eval_accuracy": 0.9683668888351694, |
|
"eval_f1": 0.9678054266835373, |
|
"eval_loss": 0.13082686066627502, |
|
"eval_precision": 0.9888318310769563, |
|
"eval_recall": 0.9476546099046701, |
|
"eval_runtime": 319.8968, |
|
"eval_samples_per_second": 181.04, |
|
"eval_steps_per_second": 22.632, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 4.7950902820044635e-05, |
|
"loss": 0.1008, |
|
"step": 704 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 4.786975045648205e-05, |
|
"loss": 0.1163, |
|
"step": 712 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 4.778859809291946e-05, |
|
"loss": 0.0985, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 4.770744572935687e-05, |
|
"loss": 0.1044, |
|
"step": 728 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 4.7626293365794284e-05, |
|
"loss": 0.0954, |
|
"step": 736 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 4.754514100223169e-05, |
|
"loss": 0.084, |
|
"step": 744 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 4.74639886386691e-05, |
|
"loss": 0.1018, |
|
"step": 752 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 4.738283627510651e-05, |
|
"loss": 0.0698, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 4.730168391154393e-05, |
|
"loss": 0.1247, |
|
"step": 768 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 4.722053154798134e-05, |
|
"loss": 0.0551, |
|
"step": 776 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 4.7139379184418745e-05, |
|
"loss": 0.0788, |
|
"step": 784 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 4.705822682085616e-05, |
|
"loss": 0.1147, |
|
"step": 792 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 4.697707445729357e-05, |
|
"loss": 0.0704, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"eval_accuracy": 0.9718720861967746, |
|
"eval_f1": 0.9722992160797185, |
|
"eval_loss": 0.08833611011505127, |
|
"eval_precision": 0.9609747899159664, |
|
"eval_recall": 0.9838937261245139, |
|
"eval_runtime": 320.3064, |
|
"eval_samples_per_second": 180.808, |
|
"eval_steps_per_second": 22.603, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 4.6895922093730985e-05, |
|
"loss": 0.1034, |
|
"step": 808 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 4.6814769730168394e-05, |
|
"loss": 0.1137, |
|
"step": 816 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 4.67336173666058e-05, |
|
"loss": 0.0647, |
|
"step": 824 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 4.665246500304322e-05, |
|
"loss": 0.1009, |
|
"step": 832 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 4.657131263948063e-05, |
|
"loss": 0.0659, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 4.6490160275918036e-05, |
|
"loss": 0.0619, |
|
"step": 848 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 4.640900791235545e-05, |
|
"loss": 0.0762, |
|
"step": 856 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 4.632785554879286e-05, |
|
"loss": 0.0348, |
|
"step": 864 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 4.624670318523027e-05, |
|
"loss": 0.0976, |
|
"step": 872 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 4.6165550821667686e-05, |
|
"loss": 0.0727, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 4.6084398458105094e-05, |
|
"loss": 0.0572, |
|
"step": 888 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 4.600324609454251e-05, |
|
"loss": 0.0582, |
|
"step": 896 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"eval_accuracy": 0.973028973995925, |
|
"eval_f1": 0.973034561336878, |
|
"eval_loss": 0.08047471195459366, |
|
"eval_precision": 0.9762028473449028, |
|
"eval_recall": 0.9698867742712599, |
|
"eval_runtime": 320.2553, |
|
"eval_samples_per_second": 180.837, |
|
"eval_steps_per_second": 22.607, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 4.592209373097991e-05, |
|
"loss": 0.098, |
|
"step": 904 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 4.584094136741733e-05, |
|
"loss": 0.1056, |
|
"step": 912 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 4.5759789003854744e-05, |
|
"loss": 0.0511, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 4.567863664029215e-05, |
|
"loss": 0.092, |
|
"step": 928 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 4.559748427672956e-05, |
|
"loss": 0.0727, |
|
"step": 936 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 4.551633191316697e-05, |
|
"loss": 0.0495, |
|
"step": 944 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 4.5435179549604386e-05, |
|
"loss": 0.0912, |
|
"step": 952 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 4.5354027186041795e-05, |
|
"loss": 0.0717, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 4.5272874822479204e-05, |
|
"loss": 0.0395, |
|
"step": 968 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 4.519172245891662e-05, |
|
"loss": 0.1236, |
|
"step": 976 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 4.511057009535403e-05, |
|
"loss": 0.1675, |
|
"step": 984 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 4.502941773179144e-05, |
|
"loss": 0.0863, |
|
"step": 992 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 4.494826536822885e-05, |
|
"loss": 0.0867, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"eval_accuracy": 0.9773457195151432, |
|
"eval_f1": 0.977261698440208, |
|
"eval_loss": 0.06294739246368408, |
|
"eval_precision": 0.984324267709388, |
|
"eval_recall": 0.9702997556526827, |
|
"eval_runtime": 318.1602, |
|
"eval_samples_per_second": 182.028, |
|
"eval_steps_per_second": 22.756, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 4.486711300466626e-05, |
|
"loss": 0.1165, |
|
"step": 1008 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 4.478596064110368e-05, |
|
"loss": 0.083, |
|
"step": 1016 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 4.470480827754109e-05, |
|
"loss": 0.083, |
|
"step": 1024 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 4.4623655913978496e-05, |
|
"loss": 0.0775, |
|
"step": 1032 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 4.454250355041591e-05, |
|
"loss": 0.0958, |
|
"step": 1040 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 4.446135118685332e-05, |
|
"loss": 0.0814, |
|
"step": 1048 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 4.438019882329073e-05, |
|
"loss": 0.0633, |
|
"step": 1056 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 4.4299046459728145e-05, |
|
"loss": 0.0876, |
|
"step": 1064 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 4.4217894096165554e-05, |
|
"loss": 0.0853, |
|
"step": 1072 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 4.413674173260296e-05, |
|
"loss": 0.0678, |
|
"step": 1080 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 4.405558936904037e-05, |
|
"loss": 0.0541, |
|
"step": 1088 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 4.397443700547779e-05, |
|
"loss": 0.1059, |
|
"step": 1096 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"eval_accuracy": 0.9705252615947785, |
|
"eval_f1": 0.9711601817905354, |
|
"eval_loss": 0.08772066235542297, |
|
"eval_precision": 0.9538364529403955, |
|
"eval_recall": 0.9891248236225351, |
|
"eval_runtime": 320.9793, |
|
"eval_samples_per_second": 180.429, |
|
"eval_steps_per_second": 22.556, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 4.38932846419152e-05, |
|
"loss": 0.0416, |
|
"step": 1104 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 4.3812132278352605e-05, |
|
"loss": 0.108, |
|
"step": 1112 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 4.373097991479002e-05, |
|
"loss": 0.0706, |
|
"step": 1120 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 4.364982755122743e-05, |
|
"loss": 0.1139, |
|
"step": 1128 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 4.3568675187664845e-05, |
|
"loss": 0.0468, |
|
"step": 1136 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 4.3487522824102254e-05, |
|
"loss": 0.113, |
|
"step": 1144 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 4.340637046053966e-05, |
|
"loss": 0.0934, |
|
"step": 1152 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 4.332521809697708e-05, |
|
"loss": 0.1363, |
|
"step": 1160 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 4.324406573341449e-05, |
|
"loss": 0.0816, |
|
"step": 1168 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 4.31629133698519e-05, |
|
"loss": 0.0846, |
|
"step": 1176 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 4.308176100628931e-05, |
|
"loss": 0.0652, |
|
"step": 1184 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 4.300060864272672e-05, |
|
"loss": 0.1003, |
|
"step": 1192 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 4.291945627916413e-05, |
|
"loss": 0.1021, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"eval_accuracy": 0.9757571571640709, |
|
"eval_f1": 0.9760752504941722, |
|
"eval_loss": 0.0945325568318367, |
|
"eval_precision": 0.966685793364161, |
|
"eval_recall": 0.9856488969955605, |
|
"eval_runtime": 324.5414, |
|
"eval_samples_per_second": 178.449, |
|
"eval_steps_per_second": 22.308, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 4.2838303915601546e-05, |
|
"loss": 0.0968, |
|
"step": 1208 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 4.2757151552038955e-05, |
|
"loss": 0.076, |
|
"step": 1216 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 4.267599918847637e-05, |
|
"loss": 0.0614, |
|
"step": 1224 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 4.259484682491377e-05, |
|
"loss": 0.0889, |
|
"step": 1232 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 4.251369446135119e-05, |
|
"loss": 0.0951, |
|
"step": 1240 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 4.2432542097788604e-05, |
|
"loss": 0.0406, |
|
"step": 1248 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 4.235138973422601e-05, |
|
"loss": 0.0786, |
|
"step": 1256 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 4.227023737066342e-05, |
|
"loss": 0.104, |
|
"step": 1264 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 4.218908500710083e-05, |
|
"loss": 0.1195, |
|
"step": 1272 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 4.210793264353825e-05, |
|
"loss": 0.0644, |
|
"step": 1280 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 4.2026780279975656e-05, |
|
"loss": 0.0485, |
|
"step": 1288 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 4.1945627916413064e-05, |
|
"loss": 0.0737, |
|
"step": 1296 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"eval_accuracy": 0.9794522913285216, |
|
"eval_f1": 0.9795680093403386, |
|
"eval_loss": 0.062313616275787354, |
|
"eval_precision": 0.9774199074867226, |
|
"eval_recall": 0.9817255738720446, |
|
"eval_runtime": 318.2777, |
|
"eval_samples_per_second": 181.961, |
|
"eval_steps_per_second": 22.747, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 4.186447555285048e-05, |
|
"loss": 0.1107, |
|
"step": 1304 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 4.178332318928789e-05, |
|
"loss": 0.0381, |
|
"step": 1312 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 4.17021708257253e-05, |
|
"loss": 0.0901, |
|
"step": 1320 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 4.1621018462162714e-05, |
|
"loss": 0.1092, |
|
"step": 1328 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 4.153986609860012e-05, |
|
"loss": 0.0992, |
|
"step": 1336 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 4.145871373503754e-05, |
|
"loss": 0.0763, |
|
"step": 1344 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 4.137756137147495e-05, |
|
"loss": 0.0871, |
|
"step": 1352 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 4.1296409007912356e-05, |
|
"loss": 0.0894, |
|
"step": 1360 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 4.121525664434977e-05, |
|
"loss": 0.0837, |
|
"step": 1368 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 4.113410428078718e-05, |
|
"loss": 0.0786, |
|
"step": 1376 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 4.105295191722459e-05, |
|
"loss": 0.0617, |
|
"step": 1384 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 4.0971799553662005e-05, |
|
"loss": 0.1143, |
|
"step": 1392 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 4.0890647190099414e-05, |
|
"loss": 0.0505, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"eval_accuracy": 0.980471043271057, |
|
"eval_f1": 0.9804956283304879, |
|
"eval_loss": 0.060013771057128906, |
|
"eval_precision": 0.9826477704804701, |
|
"eval_recall": 0.9783528925904257, |
|
"eval_runtime": 321.185, |
|
"eval_samples_per_second": 180.314, |
|
"eval_steps_per_second": 22.542, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 4.080949482653682e-05, |
|
"loss": 0.0471, |
|
"step": 1408 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 4.072834246297423e-05, |
|
"loss": 0.0651, |
|
"step": 1416 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 4.064719009941165e-05, |
|
"loss": 0.0796, |
|
"step": 1424 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 4.0566037735849064e-05, |
|
"loss": 0.0486, |
|
"step": 1432 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 4.0484885372286466e-05, |
|
"loss": 0.1081, |
|
"step": 1440 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 4.040373300872388e-05, |
|
"loss": 0.0397, |
|
"step": 1448 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 4.032258064516129e-05, |
|
"loss": 0.0586, |
|
"step": 1456 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 4.0241428281598706e-05, |
|
"loss": 0.0511, |
|
"step": 1464 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 4.0160275918036115e-05, |
|
"loss": 0.0273, |
|
"step": 1472 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 4.0079123554473524e-05, |
|
"loss": 0.09, |
|
"step": 1480 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 3.999797119091094e-05, |
|
"loss": 0.1026, |
|
"step": 1488 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 3.991681882734835e-05, |
|
"loss": 0.1159, |
|
"step": 1496 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"eval_accuracy": 0.979538626238906, |
|
"eval_f1": 0.9796374258956955, |
|
"eval_loss": 0.059322111308574677, |
|
"eval_precision": 0.9782757910632164, |
|
"eval_recall": 0.9810028564545549, |
|
"eval_runtime": 320.1061, |
|
"eval_samples_per_second": 180.921, |
|
"eval_steps_per_second": 22.618, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 3.983566646378576e-05, |
|
"loss": 0.055, |
|
"step": 1504 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 3.975451410022317e-05, |
|
"loss": 0.0556, |
|
"step": 1512 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 3.967336173666058e-05, |
|
"loss": 0.0569, |
|
"step": 1520 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 3.959220937309799e-05, |
|
"loss": 0.0622, |
|
"step": 1528 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 3.9511057009535407e-05, |
|
"loss": 0.0546, |
|
"step": 1536 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 3.9429904645972815e-05, |
|
"loss": 0.08, |
|
"step": 1544 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 3.934875228241023e-05, |
|
"loss": 0.0657, |
|
"step": 1552 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 3.926759991884763e-05, |
|
"loss": 0.0414, |
|
"step": 1560 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 3.918644755528505e-05, |
|
"loss": 0.0747, |
|
"step": 1568 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 3.9105295191722465e-05, |
|
"loss": 0.0617, |
|
"step": 1576 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 3.9024142828159874e-05, |
|
"loss": 0.0318, |
|
"step": 1584 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 3.894299046459728e-05, |
|
"loss": 0.1025, |
|
"step": 1592 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 3.886183810103469e-05, |
|
"loss": 0.1075, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"eval_accuracy": 0.9777946610491418, |
|
"eval_f1": 0.9776805859280085, |
|
"eval_loss": 0.07334825396537781, |
|
"eval_precision": 0.9861699520324919, |
|
"eval_recall": 0.969336132429363, |
|
"eval_runtime": 318.519, |
|
"eval_samples_per_second": 181.823, |
|
"eval_steps_per_second": 22.73, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 3.878068573747211e-05, |
|
"loss": 0.0735, |
|
"step": 1608 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 3.8699533373909516e-05, |
|
"loss": 0.1103, |
|
"step": 1616 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 3.8618381010346925e-05, |
|
"loss": 0.0638, |
|
"step": 1624 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 3.853722864678434e-05, |
|
"loss": 0.0608, |
|
"step": 1632 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 3.845607628322175e-05, |
|
"loss": 0.0609, |
|
"step": 1640 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 3.837492391965916e-05, |
|
"loss": 0.0606, |
|
"step": 1648 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 3.8293771556096574e-05, |
|
"loss": 0.0834, |
|
"step": 1656 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 3.821261919253398e-05, |
|
"loss": 0.0889, |
|
"step": 1664 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 3.81314668289714e-05, |
|
"loss": 0.0464, |
|
"step": 1672 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 3.805031446540881e-05, |
|
"loss": 0.0473, |
|
"step": 1680 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 3.796916210184622e-05, |
|
"loss": 0.0484, |
|
"step": 1688 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 3.788800973828363e-05, |
|
"loss": 0.0938, |
|
"step": 1696 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"eval_accuracy": 0.9813343923749007, |
|
"eval_f1": 0.9813185863648146, |
|
"eval_loss": 0.06325095146894455, |
|
"eval_precision": 0.9855595667870036, |
|
"eval_recall": 0.9771139484461575, |
|
"eval_runtime": 318.5283, |
|
"eval_samples_per_second": 181.817, |
|
"eval_steps_per_second": 22.73, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 3.780685737472104e-05, |
|
"loss": 0.0528, |
|
"step": 1704 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 3.772570501115845e-05, |
|
"loss": 0.0541, |
|
"step": 1712 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 3.7644552647595866e-05, |
|
"loss": 0.0737, |
|
"step": 1720 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 3.7563400284033275e-05, |
|
"loss": 0.0593, |
|
"step": 1728 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 3.7482247920470684e-05, |
|
"loss": 0.0866, |
|
"step": 1736 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 3.740109555690809e-05, |
|
"loss": 0.0564, |
|
"step": 1744 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 3.731994319334551e-05, |
|
"loss": 0.0599, |
|
"step": 1752 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 3.7238790829782924e-05, |
|
"loss": 0.0726, |
|
"step": 1760 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 3.7157638466220326e-05, |
|
"loss": 0.0675, |
|
"step": 1768 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 3.707648610265774e-05, |
|
"loss": 0.0783, |
|
"step": 1776 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 3.699533373909515e-05, |
|
"loss": 0.065, |
|
"step": 1784 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 3.6914181375532566e-05, |
|
"loss": 0.0599, |
|
"step": 1792 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 3.6833029011969975e-05, |
|
"loss": 0.0708, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"eval_accuracy": 0.9794695583105985, |
|
"eval_f1": 0.9794158890639337, |
|
"eval_loss": 0.06451611965894699, |
|
"eval_precision": 0.9854037483452937, |
|
"eval_recall": 0.9735003613587088, |
|
"eval_runtime": 315.4864, |
|
"eval_samples_per_second": 183.57, |
|
"eval_steps_per_second": 22.949, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 3.6751876648407384e-05, |
|
"loss": 0.0811, |
|
"step": 1808 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 3.66707242848448e-05, |
|
"loss": 0.0723, |
|
"step": 1816 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 3.658957192128221e-05, |
|
"loss": 0.0748, |
|
"step": 1824 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 3.650841955771962e-05, |
|
"loss": 0.0869, |
|
"step": 1832 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 3.6427267194157034e-05, |
|
"loss": 0.0578, |
|
"step": 1840 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 3.634611483059444e-05, |
|
"loss": 0.0813, |
|
"step": 1848 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 3.626496246703185e-05, |
|
"loss": 0.0748, |
|
"step": 1856 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 3.618381010346927e-05, |
|
"loss": 0.0686, |
|
"step": 1864 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 3.6102657739906676e-05, |
|
"loss": 0.0697, |
|
"step": 1872 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 3.602150537634409e-05, |
|
"loss": 0.0728, |
|
"step": 1880 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 3.5940353012781494e-05, |
|
"loss": 0.079, |
|
"step": 1888 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 3.585920064921891e-05, |
|
"loss": 0.0719, |
|
"step": 1896 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"eval_accuracy": 0.9799012328625203, |
|
"eval_f1": 0.9800301948943178, |
|
"eval_loss": 0.0590737946331501, |
|
"eval_precision": 0.9771133385789059, |
|
"eval_recall": 0.9829645180163128, |
|
"eval_runtime": 317.0745, |
|
"eval_samples_per_second": 182.651, |
|
"eval_steps_per_second": 22.834, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 3.5778048285656325e-05, |
|
"loss": 0.0502, |
|
"step": 1904 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 3.5696895922093734e-05, |
|
"loss": 0.0592, |
|
"step": 1912 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 3.561574355853114e-05, |
|
"loss": 0.0849, |
|
"step": 1920 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 3.553459119496855e-05, |
|
"loss": 0.1225, |
|
"step": 1928 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 3.545343883140597e-05, |
|
"loss": 0.0855, |
|
"step": 1936 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 3.5372286467843377e-05, |
|
"loss": 0.0652, |
|
"step": 1944 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 3.5291134104280785e-05, |
|
"loss": 0.0585, |
|
"step": 1952 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 3.52099817407182e-05, |
|
"loss": 0.0544, |
|
"step": 1960 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 3.512882937715561e-05, |
|
"loss": 0.0836, |
|
"step": 1968 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 3.504767701359302e-05, |
|
"loss": 0.0505, |
|
"step": 1976 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 3.4966524650030435e-05, |
|
"loss": 0.0435, |
|
"step": 1984 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 3.4885372286467844e-05, |
|
"loss": 0.078, |
|
"step": 1992 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 3.480421992290526e-05, |
|
"loss": 0.0365, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"eval_accuracy": 0.9795731602030597, |
|
"eval_f1": 0.9794998873620184, |
|
"eval_loss": 0.08517105132341385, |
|
"eval_precision": 0.986457242582897, |
|
"eval_recall": 0.9726399834807448, |
|
"eval_runtime": 319.0106, |
|
"eval_samples_per_second": 181.543, |
|
"eval_steps_per_second": 22.695, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 3.472306755934267e-05, |
|
"loss": 0.0755, |
|
"step": 2008 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 3.464191519578008e-05, |
|
"loss": 0.0446, |
|
"step": 2016 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 3.456076283221749e-05, |
|
"loss": 0.045, |
|
"step": 2024 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 3.44796104686549e-05, |
|
"loss": 0.0446, |
|
"step": 2032 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 3.439845810509231e-05, |
|
"loss": 0.0601, |
|
"step": 2040 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 3.4317305741529726e-05, |
|
"loss": 0.0784, |
|
"step": 2048 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 3.4236153377967135e-05, |
|
"loss": 0.0601, |
|
"step": 2056 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 3.4155001014404544e-05, |
|
"loss": 0.0628, |
|
"step": 2064 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 3.407384865084195e-05, |
|
"loss": 0.0805, |
|
"step": 2072 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 3.399269628727937e-05, |
|
"loss": 0.0429, |
|
"step": 2080 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 3.3911543923716785e-05, |
|
"loss": 0.0589, |
|
"step": 2088 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 3.383039156015419e-05, |
|
"loss": 0.0564, |
|
"step": 2096 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"eval_accuracy": 0.9813171253928239, |
|
"eval_f1": 0.9813274427915645, |
|
"eval_loss": 0.05837487801909447, |
|
"eval_precision": 0.9841808300737305, |
|
"eval_recall": 0.9784905530508999, |
|
"eval_runtime": 319.719, |
|
"eval_samples_per_second": 181.14, |
|
"eval_steps_per_second": 22.645, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 3.37492391965916e-05, |
|
"loss": 0.0755, |
|
"step": 2104 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 3.366808683302901e-05, |
|
"loss": 0.0578, |
|
"step": 2112 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 3.358693446946643e-05, |
|
"loss": 0.076, |
|
"step": 2120 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 3.3505782105903836e-05, |
|
"loss": 0.0767, |
|
"step": 2128 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 3.3424629742341245e-05, |
|
"loss": 0.0393, |
|
"step": 2136 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 3.334347737877866e-05, |
|
"loss": 0.057, |
|
"step": 2144 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 3.326232501521607e-05, |
|
"loss": 0.0671, |
|
"step": 2152 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 3.318117265165348e-05, |
|
"loss": 0.0338, |
|
"step": 2160 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 3.3100020288090894e-05, |
|
"loss": 0.0637, |
|
"step": 2168 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 3.30188679245283e-05, |
|
"loss": 0.0585, |
|
"step": 2176 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 3.293771556096571e-05, |
|
"loss": 0.0699, |
|
"step": 2184 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 3.285656319740313e-05, |
|
"loss": 0.0357, |
|
"step": 2192 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 3.2775410833840536e-05, |
|
"loss": 0.0951, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"eval_accuracy": 0.9820250716579756, |
|
"eval_f1": 0.9820328276290582, |
|
"eval_loss": 0.05581849440932274, |
|
"eval_precision": 0.9850079634374351, |
|
"eval_recall": 0.9790756100079154, |
|
"eval_runtime": 315.2538, |
|
"eval_samples_per_second": 183.706, |
|
"eval_steps_per_second": 22.966, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 3.269425847027795e-05, |
|
"loss": 0.0712, |
|
"step": 2208 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 3.2613106106715354e-05, |
|
"loss": 0.0666, |
|
"step": 2216 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 3.253195374315277e-05, |
|
"loss": 0.0806, |
|
"step": 2224 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 3.2450801379590186e-05, |
|
"loss": 0.0511, |
|
"step": 2232 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 3.2369649016027595e-05, |
|
"loss": 0.0523, |
|
"step": 2240 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 3.2288496652465004e-05, |
|
"loss": 0.0738, |
|
"step": 2248 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 3.220734428890241e-05, |
|
"loss": 0.0555, |
|
"step": 2256 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 3.212619192533983e-05, |
|
"loss": 0.0723, |
|
"step": 2264 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 3.204503956177724e-05, |
|
"loss": 0.0603, |
|
"step": 2272 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 3.1963887198214646e-05, |
|
"loss": 0.0477, |
|
"step": 2280 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 3.188273483465206e-05, |
|
"loss": 0.0724, |
|
"step": 2288 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 3.180158247108947e-05, |
|
"loss": 0.0909, |
|
"step": 2296 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"eval_accuracy": 0.9805573781814414, |
|
"eval_f1": 0.9807237990892596, |
|
"eval_loss": 0.05231529101729393, |
|
"eval_precision": 0.9757127771911299, |
|
"eval_recall": 0.9857865574560347, |
|
"eval_runtime": 314.1871, |
|
"eval_samples_per_second": 184.33, |
|
"eval_steps_per_second": 23.044, |
|
"step": 2300 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 3.172043010752688e-05, |
|
"loss": 0.0451, |
|
"step": 2304 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 3.1639277743964295e-05, |
|
"loss": 0.0539, |
|
"step": 2312 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 3.1558125380401704e-05, |
|
"loss": 0.0669, |
|
"step": 2320 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 3.147697301683912e-05, |
|
"loss": 0.0439, |
|
"step": 2328 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 3.139582065327653e-05, |
|
"loss": 0.0849, |
|
"step": 2336 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 3.131466828971394e-05, |
|
"loss": 0.0798, |
|
"step": 2344 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 3.123351592615135e-05, |
|
"loss": 0.0699, |
|
"step": 2352 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 3.115236356258876e-05, |
|
"loss": 0.0707, |
|
"step": 2360 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 3.107121119902617e-05, |
|
"loss": 0.0432, |
|
"step": 2368 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 3.099005883546359e-05, |
|
"loss": 0.074, |
|
"step": 2376 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 3.0908906471900996e-05, |
|
"loss": 0.091, |
|
"step": 2384 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 3.0827754108338405e-05, |
|
"loss": 0.0482, |
|
"step": 2392 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 3.0746601744775814e-05, |
|
"loss": 0.0673, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"eval_accuracy": 0.9821804744966675, |
|
"eval_f1": 0.9821866261608035, |
|
"eval_loss": 0.05170663446187973, |
|
"eval_precision": 0.9852477750458842, |
|
"eval_recall": 0.9791444402381526, |
|
"eval_runtime": 314.3647, |
|
"eval_samples_per_second": 184.226, |
|
"eval_steps_per_second": 23.031, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 3.066544938121323e-05, |
|
"loss": 0.0329, |
|
"step": 2408 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 3.0584297017650645e-05, |
|
"loss": 0.0723, |
|
"step": 2416 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 3.050314465408805e-05, |
|
"loss": 0.0806, |
|
"step": 2424 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 3.0421992290525463e-05, |
|
"loss": 0.0854, |
|
"step": 2432 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 3.0340839926962872e-05, |
|
"loss": 0.09, |
|
"step": 2440 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 3.0259687563400284e-05, |
|
"loss": 0.0537, |
|
"step": 2448 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 3.01785351998377e-05, |
|
"loss": 0.0342, |
|
"step": 2456 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 3.0097382836275105e-05, |
|
"loss": 0.0874, |
|
"step": 2464 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 3.001623047271252e-05, |
|
"loss": 0.0435, |
|
"step": 2472 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 2.9935078109149927e-05, |
|
"loss": 0.08, |
|
"step": 2480 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 2.9853925745587342e-05, |
|
"loss": 0.0496, |
|
"step": 2488 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 2.9772773382024755e-05, |
|
"loss": 0.0338, |
|
"step": 2496 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"eval_accuracy": 0.9790551507407536, |
|
"eval_f1": 0.9788532278028625, |
|
"eval_loss": 0.07079575955867767, |
|
"eval_precision": 0.9918739400791408, |
|
"eval_recall": 0.9661699418384555, |
|
"eval_runtime": 321.7416, |
|
"eval_samples_per_second": 180.002, |
|
"eval_steps_per_second": 22.503, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 2.9691621018462163e-05, |
|
"loss": 0.1099, |
|
"step": 2504 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 2.9610468654899576e-05, |
|
"loss": 0.0828, |
|
"step": 2512 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 2.9529316291336988e-05, |
|
"loss": 0.0722, |
|
"step": 2520 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 2.9448163927774397e-05, |
|
"loss": 0.0693, |
|
"step": 2528 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 2.936701156421181e-05, |
|
"loss": 0.0606, |
|
"step": 2536 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 2.9285859200649218e-05, |
|
"loss": 0.0794, |
|
"step": 2544 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 2.920470683708663e-05, |
|
"loss": 0.0794, |
|
"step": 2552 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 2.9123554473524046e-05, |
|
"loss": 0.0353, |
|
"step": 2560 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 2.9042402109961452e-05, |
|
"loss": 0.087, |
|
"step": 2568 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 2.8961249746398867e-05, |
|
"loss": 0.0708, |
|
"step": 2576 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 2.8880097382836273e-05, |
|
"loss": 0.102, |
|
"step": 2584 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 2.879894501927369e-05, |
|
"loss": 0.0967, |
|
"step": 2592 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 2.87177926557111e-05, |
|
"loss": 0.0528, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"eval_accuracy": 0.9754981524329178, |
|
"eval_f1": 0.9751056999000018, |
|
"eval_loss": 0.06617435812950134, |
|
"eval_precision": 0.994524763813341, |
|
"eval_recall": 0.956430464259903, |
|
"eval_runtime": 317.2016, |
|
"eval_samples_per_second": 182.578, |
|
"eval_steps_per_second": 22.825, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 2.863664029214851e-05, |
|
"loss": 0.0414, |
|
"step": 2608 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 2.8555487928585922e-05, |
|
"loss": 0.0709, |
|
"step": 2616 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 2.847433556502333e-05, |
|
"loss": 0.0676, |
|
"step": 2624 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 2.8393183201460743e-05, |
|
"loss": 0.0444, |
|
"step": 2632 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 2.8312030837898156e-05, |
|
"loss": 0.074, |
|
"step": 2640 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 2.8230878474335565e-05, |
|
"loss": 0.0723, |
|
"step": 2648 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 2.8149726110772977e-05, |
|
"loss": 0.0471, |
|
"step": 2656 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 2.8068573747210393e-05, |
|
"loss": 0.0475, |
|
"step": 2664 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 2.7987421383647798e-05, |
|
"loss": 0.0507, |
|
"step": 2672 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 2.7906269020085214e-05, |
|
"loss": 0.0465, |
|
"step": 2680 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 2.782511665652262e-05, |
|
"loss": 0.0358, |
|
"step": 2688 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 2.7743964292960035e-05, |
|
"loss": 0.0662, |
|
"step": 2696 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"eval_accuracy": 0.9828020858514349, |
|
"eval_f1": 0.9828204774389403, |
|
"eval_loss": 0.05437169969081879, |
|
"eval_precision": 0.9851654621529099, |
|
"eval_recall": 0.9804866297277764, |
|
"eval_runtime": 318.7613, |
|
"eval_samples_per_second": 181.685, |
|
"eval_steps_per_second": 22.713, |
|
"step": 2700 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 2.7662811929397447e-05, |
|
"loss": 0.0568, |
|
"step": 2704 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 2.7581659565834856e-05, |
|
"loss": 0.0558, |
|
"step": 2712 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 2.750050720227227e-05, |
|
"loss": 0.0535, |
|
"step": 2720 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 2.7419354838709678e-05, |
|
"loss": 0.0641, |
|
"step": 2728 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 2.733820247514709e-05, |
|
"loss": 0.0529, |
|
"step": 2736 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 2.7257050111584502e-05, |
|
"loss": 0.0754, |
|
"step": 2744 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 2.717589774802191e-05, |
|
"loss": 0.0746, |
|
"step": 2752 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 2.7094745384459323e-05, |
|
"loss": 0.0752, |
|
"step": 2760 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 2.7013593020896732e-05, |
|
"loss": 0.0733, |
|
"step": 2768 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 2.6932440657334145e-05, |
|
"loss": 0.0418, |
|
"step": 2776 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 2.685128829377156e-05, |
|
"loss": 0.0575, |
|
"step": 2784 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 2.6770135930208966e-05, |
|
"loss": 0.0463, |
|
"step": 2792 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 2.668898356664638e-05, |
|
"loss": 0.0606, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"eval_accuracy": 0.9828711537797423, |
|
"eval_f1": 0.9828776581054958, |
|
"eval_loss": 0.052921637892723083, |
|
"eval_precision": 0.9859067142214065, |
|
"eval_recall": 0.9798671576556424, |
|
"eval_runtime": 324.5523, |
|
"eval_samples_per_second": 178.443, |
|
"eval_steps_per_second": 22.308, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 2.6607831203083787e-05, |
|
"loss": 0.0665, |
|
"step": 2808 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 2.6526678839521203e-05, |
|
"loss": 0.0533, |
|
"step": 2816 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 2.6445526475958615e-05, |
|
"loss": 0.0706, |
|
"step": 2824 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 2.6364374112396024e-05, |
|
"loss": 0.0729, |
|
"step": 2832 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 2.6283221748833436e-05, |
|
"loss": 0.0498, |
|
"step": 2840 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 2.620206938527085e-05, |
|
"loss": 0.0438, |
|
"step": 2848 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 2.6120917021708257e-05, |
|
"loss": 0.0599, |
|
"step": 2856 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 2.603976465814567e-05, |
|
"loss": 0.0413, |
|
"step": 2864 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 2.595861229458308e-05, |
|
"loss": 0.0323, |
|
"step": 2872 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 2.587745993102049e-05, |
|
"loss": 0.0706, |
|
"step": 2880 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 2.5796307567457907e-05, |
|
"loss": 0.116, |
|
"step": 2888 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 2.5715155203895312e-05, |
|
"loss": 0.0585, |
|
"step": 2896 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"eval_accuracy": 0.9815415961598232, |
|
"eval_f1": 0.9814451599465398, |
|
"eval_loss": 0.0516064278781414, |
|
"eval_precision": 0.99005462949993, |
|
"eval_recall": 0.9729841346319303, |
|
"eval_runtime": 325.834, |
|
"eval_samples_per_second": 177.741, |
|
"eval_steps_per_second": 22.22, |
|
"step": 2900 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 2.5634002840332728e-05, |
|
"loss": 0.0475, |
|
"step": 2904 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 2.5552850476770133e-05, |
|
"loss": 0.0612, |
|
"step": 2912 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 2.547169811320755e-05, |
|
"loss": 0.0558, |
|
"step": 2920 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 2.539054574964496e-05, |
|
"loss": 0.0572, |
|
"step": 2928 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 2.530939338608237e-05, |
|
"loss": 0.0581, |
|
"step": 2936 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 2.5228241022519783e-05, |
|
"loss": 0.0487, |
|
"step": 2944 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 2.514708865895719e-05, |
|
"loss": 0.0681, |
|
"step": 2952 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 2.5065936295394604e-05, |
|
"loss": 0.0658, |
|
"step": 2960 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 2.4984783931832016e-05, |
|
"loss": 0.0769, |
|
"step": 2968 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 2.490363156826943e-05, |
|
"loss": 0.0736, |
|
"step": 2976 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 2.4822479204706837e-05, |
|
"loss": 0.0446, |
|
"step": 2984 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 2.474132684114425e-05, |
|
"loss": 0.0472, |
|
"step": 2992 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 2.466017447758166e-05, |
|
"loss": 0.058, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"eval_accuracy": 0.9817142659805919, |
|
"eval_f1": 0.981694352733747, |
|
"eval_loss": 0.061614930629730225, |
|
"eval_precision": 0.9861776759047024, |
|
"eval_recall": 0.9772516089066318, |
|
"eval_runtime": 317.9761, |
|
"eval_samples_per_second": 182.133, |
|
"eval_steps_per_second": 22.769, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 2.457902211401907e-05, |
|
"loss": 0.0432, |
|
"step": 3008 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 2.4497869750456483e-05, |
|
"loss": 0.0392, |
|
"step": 3016 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 2.4416717386893896e-05, |
|
"loss": 0.0581, |
|
"step": 3024 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 2.4335565023331305e-05, |
|
"loss": 0.0642, |
|
"step": 3032 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 2.4254412659768717e-05, |
|
"loss": 0.039, |
|
"step": 3040 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 2.417326029620613e-05, |
|
"loss": 0.0361, |
|
"step": 3048 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 2.409210793264354e-05, |
|
"loss": 0.0591, |
|
"step": 3056 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 2.401095556908095e-05, |
|
"loss": 0.0819, |
|
"step": 3064 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 2.3929803205518363e-05, |
|
"loss": 0.1084, |
|
"step": 3072 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 2.384865084195577e-05, |
|
"loss": 0.0425, |
|
"step": 3080 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 2.3767498478393184e-05, |
|
"loss": 0.0711, |
|
"step": 3088 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 2.3686346114830596e-05, |
|
"loss": 0.0449, |
|
"step": 3096 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"eval_accuracy": 0.9834064302241254, |
|
"eval_f1": 0.9835052608091176, |
|
"eval_loss": 0.04805440455675125, |
|
"eval_precision": 0.9810299958909738, |
|
"eval_recall": 0.985993048146746, |
|
"eval_runtime": 326.0918, |
|
"eval_samples_per_second": 177.6, |
|
"eval_steps_per_second": 22.202, |
|
"step": 3100 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 2.3605193751268005e-05, |
|
"loss": 0.0558, |
|
"step": 3104 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 2.3524041387705417e-05, |
|
"loss": 0.0629, |
|
"step": 3112 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 2.344288902414283e-05, |
|
"loss": 0.0392, |
|
"step": 3120 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 2.3361736660580242e-05, |
|
"loss": 0.0564, |
|
"step": 3128 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 2.328058429701765e-05, |
|
"loss": 0.0418, |
|
"step": 3136 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 2.3199431933455063e-05, |
|
"loss": 0.059, |
|
"step": 3144 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 2.3118279569892472e-05, |
|
"loss": 0.0511, |
|
"step": 3152 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 2.3037127206329888e-05, |
|
"loss": 0.0383, |
|
"step": 3160 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 2.2955974842767297e-05, |
|
"loss": 0.0831, |
|
"step": 3168 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 2.287482247920471e-05, |
|
"loss": 0.0407, |
|
"step": 3176 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 2.2793670115642118e-05, |
|
"loss": 0.0354, |
|
"step": 3184 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 2.271251775207953e-05, |
|
"loss": 0.0524, |
|
"step": 3192 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 2.2631365388516943e-05, |
|
"loss": 0.0257, |
|
"step": 3200 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"eval_accuracy": 0.9817315329626688, |
|
"eval_f1": 0.9816478751084129, |
|
"eval_loss": 0.06091897934675217, |
|
"eval_precision": 0.9896128423040604, |
|
"eval_recall": 0.9738100973947758, |
|
"eval_runtime": 313.118, |
|
"eval_samples_per_second": 184.959, |
|
"eval_steps_per_second": 23.122, |
|
"step": 3200 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 2.255021302495435e-05, |
|
"loss": 0.0473, |
|
"step": 3208 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 2.2469060661391764e-05, |
|
"loss": 0.0779, |
|
"step": 3216 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 2.2387908297829173e-05, |
|
"loss": 0.0436, |
|
"step": 3224 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 2.230675593426659e-05, |
|
"loss": 0.0541, |
|
"step": 3232 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 2.2225603570703997e-05, |
|
"loss": 0.0576, |
|
"step": 3240 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 2.214445120714141e-05, |
|
"loss": 0.0649, |
|
"step": 3248 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 2.206329884357882e-05, |
|
"loss": 0.0404, |
|
"step": 3256 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 2.198214648001623e-05, |
|
"loss": 0.0351, |
|
"step": 3264 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 2.1900994116453643e-05, |
|
"loss": 0.0364, |
|
"step": 3272 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 2.1819841752891055e-05, |
|
"loss": 0.0483, |
|
"step": 3280 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 2.1738689389328464e-05, |
|
"loss": 0.0562, |
|
"step": 3288 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 2.1657537025765877e-05, |
|
"loss": 0.0627, |
|
"step": 3296 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"eval_accuracy": 0.9826121490485893, |
|
"eval_f1": 0.9827441438045136, |
|
"eval_loss": 0.04961591958999634, |
|
"eval_precision": 0.9786689419795221, |
|
"eval_recall": 0.98685342602471, |
|
"eval_runtime": 320.6595, |
|
"eval_samples_per_second": 180.609, |
|
"eval_steps_per_second": 22.578, |
|
"step": 3300 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 2.157638466220329e-05, |
|
"loss": 0.0339, |
|
"step": 3304 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 2.1495232298640698e-05, |
|
"loss": 0.0618, |
|
"step": 3312 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 2.141407993507811e-05, |
|
"loss": 0.074, |
|
"step": 3320 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 2.133292757151552e-05, |
|
"loss": 0.0781, |
|
"step": 3328 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 2.125177520795293e-05, |
|
"loss": 0.059, |
|
"step": 3336 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 2.1170622844390344e-05, |
|
"loss": 0.0411, |
|
"step": 3344 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 2.1089470480827756e-05, |
|
"loss": 0.0604, |
|
"step": 3352 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 2.1008318117265165e-05, |
|
"loss": 0.0602, |
|
"step": 3360 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 2.0927165753702577e-05, |
|
"loss": 0.035, |
|
"step": 3368 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 2.084601339013999e-05, |
|
"loss": 0.0545, |
|
"step": 3376 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 2.0764861026577402e-05, |
|
"loss": 0.05, |
|
"step": 3384 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 2.068370866301481e-05, |
|
"loss": 0.0676, |
|
"step": 3392 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 2.0602556299452223e-05, |
|
"loss": 0.0501, |
|
"step": 3400 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"eval_accuracy": 0.9837863038298166, |
|
"eval_f1": 0.9838000103514312, |
|
"eval_loss": 0.04516952857375145, |
|
"eval_precision": 0.9863696118452916, |
|
"eval_recall": 0.9812437622603848, |
|
"eval_runtime": 311.4407, |
|
"eval_samples_per_second": 185.955, |
|
"eval_steps_per_second": 23.247, |
|
"step": 3400 |
|
} |
|
], |
|
"max_steps": 5429, |
|
"num_train_epochs": 1, |
|
"total_flos": 5.7252965646336e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|