| { | |
| "best_metric": 0.13341853022575378, | |
| "best_model_checkpoint": "Emotion-Classification/checkpoint-1000", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.024, | |
| "grad_norm": 4.761784076690674, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 1.8584, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.048, | |
| "grad_norm": 5.941750526428223, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 1.8129, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.072, | |
| "grad_norm": 5.263009071350098, | |
| "learning_rate": 7.2e-06, | |
| "loss": 1.7576, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 3.814999580383301, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 1.6755, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 4.710057735443115, | |
| "learning_rate": 1.2e-05, | |
| "loss": 1.651, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.144, | |
| "grad_norm": 4.196522235870361, | |
| "learning_rate": 1.44e-05, | |
| "loss": 1.6415, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.168, | |
| "grad_norm": 4.069035053253174, | |
| "learning_rate": 1.6800000000000002e-05, | |
| "loss": 1.6045, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 2.729994535446167, | |
| "learning_rate": 1.9200000000000003e-05, | |
| "loss": 1.5199, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.216, | |
| "grad_norm": 3.651451349258423, | |
| "learning_rate": 2.16e-05, | |
| "loss": 1.5483, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 3.8345696926116943, | |
| "learning_rate": 2.4e-05, | |
| "loss": 1.4484, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.264, | |
| "grad_norm": 5.036585807800293, | |
| "learning_rate": 2.64e-05, | |
| "loss": 1.352, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.288, | |
| "grad_norm": 4.797017574310303, | |
| "learning_rate": 2.88e-05, | |
| "loss": 1.2928, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.312, | |
| "grad_norm": 4.072025299072266, | |
| "learning_rate": 3.12e-05, | |
| "loss": 1.2858, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.336, | |
| "grad_norm": 4.3313727378845215, | |
| "learning_rate": 3.3600000000000004e-05, | |
| "loss": 1.1242, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 5.59000825881958, | |
| "learning_rate": 3.56e-05, | |
| "loss": 1.1086, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.384, | |
| "grad_norm": 8.562559127807617, | |
| "learning_rate": 3.8e-05, | |
| "loss": 0.9659, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.408, | |
| "grad_norm": 7.202652931213379, | |
| "learning_rate": 4.0400000000000006e-05, | |
| "loss": 0.9103, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.432, | |
| "grad_norm": 6.920612812042236, | |
| "learning_rate": 4.2800000000000004e-05, | |
| "loss": 0.8257, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.456, | |
| "grad_norm": 4.389594078063965, | |
| "learning_rate": 4.52e-05, | |
| "loss": 0.7882, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 8.991690635681152, | |
| "learning_rate": 4.76e-05, | |
| "loss": 0.7142, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.504, | |
| "grad_norm": 5.250122547149658, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6461, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.528, | |
| "grad_norm": 6.273474216461182, | |
| "learning_rate": 4.973333333333334e-05, | |
| "loss": 0.6108, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.552, | |
| "grad_norm": 5.45080041885376, | |
| "learning_rate": 4.9466666666666665e-05, | |
| "loss": 0.5098, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.576, | |
| "grad_norm": 6.3116068840026855, | |
| "learning_rate": 4.92e-05, | |
| "loss": 0.4719, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 9.022950172424316, | |
| "learning_rate": 4.8933333333333335e-05, | |
| "loss": 0.3653, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.624, | |
| "grad_norm": 6.852407455444336, | |
| "learning_rate": 4.866666666666667e-05, | |
| "loss": 0.4934, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.648, | |
| "grad_norm": 4.436535835266113, | |
| "learning_rate": 4.8400000000000004e-05, | |
| "loss": 0.3817, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.672, | |
| "grad_norm": 5.454000949859619, | |
| "learning_rate": 4.8133333333333336e-05, | |
| "loss": 0.3123, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.696, | |
| "grad_norm": 6.807215690612793, | |
| "learning_rate": 4.7866666666666674e-05, | |
| "loss": 0.2737, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 4.130777835845947, | |
| "learning_rate": 4.76e-05, | |
| "loss": 0.3287, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.744, | |
| "grad_norm": 15.173467636108398, | |
| "learning_rate": 4.7333333333333336e-05, | |
| "loss": 0.2525, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.768, | |
| "grad_norm": 3.7970285415649414, | |
| "learning_rate": 4.706666666666667e-05, | |
| "loss": 0.3568, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.792, | |
| "grad_norm": 3.6102640628814697, | |
| "learning_rate": 4.6800000000000006e-05, | |
| "loss": 0.2952, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.816, | |
| "grad_norm": 2.048801898956299, | |
| "learning_rate": 4.653333333333334e-05, | |
| "loss": 0.3303, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 9.570277214050293, | |
| "learning_rate": 4.626666666666667e-05, | |
| "loss": 0.2736, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.864, | |
| "grad_norm": 3.7270052433013916, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 0.2399, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.888, | |
| "grad_norm": 2.341561794281006, | |
| "learning_rate": 4.573333333333333e-05, | |
| "loss": 0.2085, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.912, | |
| "grad_norm": 3.1725029945373535, | |
| "learning_rate": 4.546666666666667e-05, | |
| "loss": 0.2126, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.936, | |
| "grad_norm": 9.990570068359375, | |
| "learning_rate": 4.52e-05, | |
| "loss": 0.2663, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 3.6300106048583984, | |
| "learning_rate": 4.493333333333333e-05, | |
| "loss": 0.2006, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.984, | |
| "grad_norm": 2.360503911972046, | |
| "learning_rate": 4.466666666666667e-05, | |
| "loss": 0.2727, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9215, | |
| "eval_f1_macro": 0.8995337377920993, | |
| "eval_f1_micro": 0.9215, | |
| "eval_f1_weighted": 0.9231309624099143, | |
| "eval_loss": 0.23581676185131073, | |
| "eval_precision_macro": 0.8849160410790557, | |
| "eval_precision_micro": 0.9215, | |
| "eval_precision_weighted": 0.9309033739712098, | |
| "eval_recall_macro": 0.9233031833590024, | |
| "eval_recall_micro": 0.9215, | |
| "eval_recall_weighted": 0.9215, | |
| "eval_runtime": 3.3949, | |
| "eval_samples_per_second": 589.114, | |
| "eval_steps_per_second": 4.713, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.008, | |
| "grad_norm": 4.654928684234619, | |
| "learning_rate": 4.44e-05, | |
| "loss": 0.2359, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 1.032, | |
| "grad_norm": 6.218105792999268, | |
| "learning_rate": 4.417777777777778e-05, | |
| "loss": 0.1733, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 1.056, | |
| "grad_norm": 5.516075611114502, | |
| "learning_rate": 4.3911111111111116e-05, | |
| "loss": 0.1447, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 5.734640598297119, | |
| "learning_rate": 4.364444444444445e-05, | |
| "loss": 0.1913, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.104, | |
| "grad_norm": 4.150918006896973, | |
| "learning_rate": 4.337777777777778e-05, | |
| "loss": 0.1179, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 1.1280000000000001, | |
| "grad_norm": 3.250934362411499, | |
| "learning_rate": 4.311111111111111e-05, | |
| "loss": 0.1777, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 1.152, | |
| "grad_norm": 4.020536422729492, | |
| "learning_rate": 4.284444444444445e-05, | |
| "loss": 0.2122, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 1.176, | |
| "grad_norm": 3.2493388652801514, | |
| "learning_rate": 4.257777777777778e-05, | |
| "loss": 0.2012, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 4.640542984008789, | |
| "learning_rate": 4.231111111111111e-05, | |
| "loss": 0.1433, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.224, | |
| "grad_norm": 3.5592172145843506, | |
| "learning_rate": 4.204444444444445e-05, | |
| "loss": 0.1534, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 1.248, | |
| "grad_norm": 5.752802848815918, | |
| "learning_rate": 4.177777777777778e-05, | |
| "loss": 0.1625, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.272, | |
| "grad_norm": 5.988048553466797, | |
| "learning_rate": 4.151111111111111e-05, | |
| "loss": 0.1654, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.296, | |
| "grad_norm": 3.1433417797088623, | |
| "learning_rate": 4.124444444444444e-05, | |
| "loss": 0.1507, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 2.363762617111206, | |
| "learning_rate": 4.097777777777778e-05, | |
| "loss": 0.1343, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.3439999999999999, | |
| "grad_norm": 2.4271459579467773, | |
| "learning_rate": 4.071111111111111e-05, | |
| "loss": 0.1354, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 1.3679999999999999, | |
| "grad_norm": 5.531872749328613, | |
| "learning_rate": 4.0444444444444444e-05, | |
| "loss": 0.2238, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 1.392, | |
| "grad_norm": 2.654528856277466, | |
| "learning_rate": 4.017777777777778e-05, | |
| "loss": 0.1248, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 1.416, | |
| "grad_norm": 2.4685096740722656, | |
| "learning_rate": 3.9911111111111114e-05, | |
| "loss": 0.142, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 11.145745277404785, | |
| "learning_rate": 3.9644444444444445e-05, | |
| "loss": 0.1379, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.464, | |
| "grad_norm": 10.70506477355957, | |
| "learning_rate": 3.937777777777778e-05, | |
| "loss": 0.0927, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 1.488, | |
| "grad_norm": 1.3703113794326782, | |
| "learning_rate": 3.9111111111111115e-05, | |
| "loss": 0.2147, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 1.512, | |
| "grad_norm": 2.9787039756774902, | |
| "learning_rate": 3.8844444444444446e-05, | |
| "loss": 0.1816, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 1.536, | |
| "grad_norm": 4.429356575012207, | |
| "learning_rate": 3.857777777777778e-05, | |
| "loss": 0.1271, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 2.4006407260894775, | |
| "learning_rate": 3.8311111111111115e-05, | |
| "loss": 0.1266, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.584, | |
| "grad_norm": 2.01302170753479, | |
| "learning_rate": 3.804444444444445e-05, | |
| "loss": 0.0847, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 1.608, | |
| "grad_norm": 2.242461681365967, | |
| "learning_rate": 3.777777777777778e-05, | |
| "loss": 0.1802, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 1.6320000000000001, | |
| "grad_norm": 1.8448535203933716, | |
| "learning_rate": 3.7511111111111116e-05, | |
| "loss": 0.1713, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 1.6560000000000001, | |
| "grad_norm": 2.21156907081604, | |
| "learning_rate": 3.724444444444445e-05, | |
| "loss": 0.1656, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 1.6800000000000002, | |
| "grad_norm": 4.768124580383301, | |
| "learning_rate": 3.697777777777778e-05, | |
| "loss": 0.1453, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.704, | |
| "grad_norm": 3.267815351486206, | |
| "learning_rate": 3.671111111111111e-05, | |
| "loss": 0.1755, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 1.728, | |
| "grad_norm": 1.797162652015686, | |
| "learning_rate": 3.644444444444445e-05, | |
| "loss": 0.1503, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 1.752, | |
| "grad_norm": 2.245846748352051, | |
| "learning_rate": 3.617777777777778e-05, | |
| "loss": 0.139, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 1.776, | |
| "grad_norm": 4.633366107940674, | |
| "learning_rate": 3.591111111111111e-05, | |
| "loss": 0.1298, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 4.398362636566162, | |
| "learning_rate": 3.564444444444445e-05, | |
| "loss": 0.1703, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.8239999999999998, | |
| "grad_norm": 4.176144599914551, | |
| "learning_rate": 3.537777777777778e-05, | |
| "loss": 0.1503, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 1.8479999999999999, | |
| "grad_norm": 6.216207027435303, | |
| "learning_rate": 3.511111111111111e-05, | |
| "loss": 0.1558, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 1.8719999999999999, | |
| "grad_norm": 2.794733762741089, | |
| "learning_rate": 3.4844444444444444e-05, | |
| "loss": 0.1679, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 1.896, | |
| "grad_norm": 6.9759392738342285, | |
| "learning_rate": 3.457777777777778e-05, | |
| "loss": 0.1304, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 1.3952761888504028, | |
| "learning_rate": 3.431111111111111e-05, | |
| "loss": 0.1418, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.944, | |
| "grad_norm": 1.8202506303787231, | |
| "learning_rate": 3.4044444444444445e-05, | |
| "loss": 0.1188, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 1.968, | |
| "grad_norm": 4.880939483642578, | |
| "learning_rate": 3.377777777777778e-05, | |
| "loss": 0.1252, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 1.992, | |
| "grad_norm": 1.7853918075561523, | |
| "learning_rate": 3.3511111111111114e-05, | |
| "loss": 0.1397, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9395, | |
| "eval_f1_macro": 0.9106849947356129, | |
| "eval_f1_micro": 0.9395, | |
| "eval_f1_weighted": 0.9383774262681576, | |
| "eval_loss": 0.14122824370861053, | |
| "eval_precision_macro": 0.9324340670283836, | |
| "eval_precision_micro": 0.9395, | |
| "eval_precision_weighted": 0.9408265963501754, | |
| "eval_recall_macro": 0.8951750793370938, | |
| "eval_recall_micro": 0.9395, | |
| "eval_recall_weighted": 0.9395, | |
| "eval_runtime": 3.4115, | |
| "eval_samples_per_second": 586.256, | |
| "eval_steps_per_second": 4.69, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.016, | |
| "grad_norm": 3.5379767417907715, | |
| "learning_rate": 3.3244444444444445e-05, | |
| "loss": 0.1067, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "grad_norm": 1.8406476974487305, | |
| "learning_rate": 3.297777777777778e-05, | |
| "loss": 0.1038, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.064, | |
| "grad_norm": 1.2835277318954468, | |
| "learning_rate": 3.2711111111111115e-05, | |
| "loss": 0.0894, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 2.088, | |
| "grad_norm": 0.9669094085693359, | |
| "learning_rate": 3.2444444444444446e-05, | |
| "loss": 0.0914, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 2.112, | |
| "grad_norm": 1.4967998266220093, | |
| "learning_rate": 3.217777777777778e-05, | |
| "loss": 0.115, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 2.136, | |
| "grad_norm": 0.5459607243537903, | |
| "learning_rate": 3.1911111111111116e-05, | |
| "loss": 0.1238, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "grad_norm": 0.6286458969116211, | |
| "learning_rate": 3.164444444444444e-05, | |
| "loss": 0.078, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.184, | |
| "grad_norm": 0.8293291926383972, | |
| "learning_rate": 3.137777777777778e-05, | |
| "loss": 0.0956, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 2.208, | |
| "grad_norm": 1.015953779220581, | |
| "learning_rate": 3.111111111111111e-05, | |
| "loss": 0.1022, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 2.232, | |
| "grad_norm": 0.6408522129058838, | |
| "learning_rate": 3.084444444444445e-05, | |
| "loss": 0.0839, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 2.2560000000000002, | |
| "grad_norm": 1.495943307876587, | |
| "learning_rate": 3.057777777777778e-05, | |
| "loss": 0.0937, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 2.2800000000000002, | |
| "grad_norm": 1.8174567222595215, | |
| "learning_rate": 3.031111111111111e-05, | |
| "loss": 0.1216, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.304, | |
| "grad_norm": 0.502436637878418, | |
| "learning_rate": 3.004444444444445e-05, | |
| "loss": 0.0754, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 2.328, | |
| "grad_norm": 5.995917320251465, | |
| "learning_rate": 2.9777777777777777e-05, | |
| "loss": 0.164, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 2.352, | |
| "grad_norm": 1.4363820552825928, | |
| "learning_rate": 2.951111111111111e-05, | |
| "loss": 0.1006, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 2.376, | |
| "grad_norm": 0.8328127861022949, | |
| "learning_rate": 2.9244444444444446e-05, | |
| "loss": 0.0861, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 0.8516309261322021, | |
| "learning_rate": 2.897777777777778e-05, | |
| "loss": 0.0852, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.424, | |
| "grad_norm": 1.308616042137146, | |
| "learning_rate": 2.8711111111111113e-05, | |
| "loss": 0.0785, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 2.448, | |
| "grad_norm": 2.7151458263397217, | |
| "learning_rate": 2.8444444444444447e-05, | |
| "loss": 0.1236, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 2.472, | |
| "grad_norm": 0.8587580919265747, | |
| "learning_rate": 2.8177777777777782e-05, | |
| "loss": 0.0841, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 2.496, | |
| "grad_norm": 2.1243529319763184, | |
| "learning_rate": 2.791111111111111e-05, | |
| "loss": 0.0769, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "grad_norm": 1.7264567613601685, | |
| "learning_rate": 2.7644444444444445e-05, | |
| "loss": 0.1453, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.544, | |
| "grad_norm": 0.745203971862793, | |
| "learning_rate": 2.737777777777778e-05, | |
| "loss": 0.0685, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 2.568, | |
| "grad_norm": 1.8616527318954468, | |
| "learning_rate": 2.7111111111111114e-05, | |
| "loss": 0.1152, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 2.592, | |
| "grad_norm": 1.0319263935089111, | |
| "learning_rate": 2.6844444444444446e-05, | |
| "loss": 0.0866, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 2.616, | |
| "grad_norm": 1.321435809135437, | |
| "learning_rate": 2.657777777777778e-05, | |
| "loss": 0.0979, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "grad_norm": 0.6810425519943237, | |
| "learning_rate": 2.6311111111111115e-05, | |
| "loss": 0.0746, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.664, | |
| "grad_norm": 4.602859020233154, | |
| "learning_rate": 2.6044444444444443e-05, | |
| "loss": 0.1134, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.6879999999999997, | |
| "grad_norm": 0.9797782301902771, | |
| "learning_rate": 2.5777777777777778e-05, | |
| "loss": 0.0779, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 2.7119999999999997, | |
| "grad_norm": 3.393965005874634, | |
| "learning_rate": 2.5511111111111113e-05, | |
| "loss": 0.1137, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 2.7359999999999998, | |
| "grad_norm": 1.6358873844146729, | |
| "learning_rate": 2.5244444444444447e-05, | |
| "loss": 0.0829, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "grad_norm": 0.8677324056625366, | |
| "learning_rate": 2.497777777777778e-05, | |
| "loss": 0.0655, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.784, | |
| "grad_norm": 2.418769121170044, | |
| "learning_rate": 2.4711111111111114e-05, | |
| "loss": 0.0726, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 2.808, | |
| "grad_norm": 1.677323341369629, | |
| "learning_rate": 2.4444444444444445e-05, | |
| "loss": 0.0694, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 2.832, | |
| "grad_norm": 1.2437670230865479, | |
| "learning_rate": 2.417777777777778e-05, | |
| "loss": 0.0986, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 2.856, | |
| "grad_norm": 2.447063684463501, | |
| "learning_rate": 2.391111111111111e-05, | |
| "loss": 0.1185, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 0.7579317092895508, | |
| "learning_rate": 2.3644444444444446e-05, | |
| "loss": 0.0932, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.904, | |
| "grad_norm": 1.1533098220825195, | |
| "learning_rate": 2.337777777777778e-05, | |
| "loss": 0.1013, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 2.928, | |
| "grad_norm": 0.8839074969291687, | |
| "learning_rate": 2.3111111111111112e-05, | |
| "loss": 0.0912, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 2.952, | |
| "grad_norm": 1.182469129562378, | |
| "learning_rate": 2.2844444444444447e-05, | |
| "loss": 0.0901, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 2.976, | |
| "grad_norm": 0.9109925627708435, | |
| "learning_rate": 2.2577777777777778e-05, | |
| "loss": 0.0785, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 1.4611146450042725, | |
| "learning_rate": 2.2311111111111113e-05, | |
| "loss": 0.0768, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.942, | |
| "eval_f1_macro": 0.9199698545563004, | |
| "eval_f1_micro": 0.942, | |
| "eval_f1_weighted": 0.942299793738485, | |
| "eval_loss": 0.13686497509479523, | |
| "eval_precision_macro": 0.912222911519835, | |
| "eval_precision_micro": 0.942, | |
| "eval_precision_weighted": 0.9429745034281065, | |
| "eval_recall_macro": 0.9287782509639695, | |
| "eval_recall_micro": 0.942, | |
| "eval_recall_weighted": 0.942, | |
| "eval_runtime": 3.3845, | |
| "eval_samples_per_second": 590.924, | |
| "eval_steps_per_second": 4.727, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.024, | |
| "grad_norm": 5.040261745452881, | |
| "learning_rate": 2.2044444444444444e-05, | |
| "loss": 0.078, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 3.048, | |
| "grad_norm": 0.5013237595558167, | |
| "learning_rate": 2.177777777777778e-05, | |
| "loss": 0.0558, | |
| "step": 762 | |
| }, | |
| { | |
| "epoch": 3.072, | |
| "grad_norm": 1.1819310188293457, | |
| "learning_rate": 2.1511111111111114e-05, | |
| "loss": 0.0682, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 3.096, | |
| "grad_norm": 0.9416047930717468, | |
| "learning_rate": 2.1244444444444445e-05, | |
| "loss": 0.0775, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "grad_norm": 2.0191128253936768, | |
| "learning_rate": 2.097777777777778e-05, | |
| "loss": 0.0645, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 3.144, | |
| "grad_norm": 3.3059170246124268, | |
| "learning_rate": 2.071111111111111e-05, | |
| "loss": 0.0713, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 3.168, | |
| "grad_norm": 0.6508151888847351, | |
| "learning_rate": 2.0444444444444446e-05, | |
| "loss": 0.0631, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 3.192, | |
| "grad_norm": 0.7478683590888977, | |
| "learning_rate": 2.0177777777777777e-05, | |
| "loss": 0.0826, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 3.216, | |
| "grad_norm": 0.5315937995910645, | |
| "learning_rate": 1.9911111111111112e-05, | |
| "loss": 0.0599, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "grad_norm": 0.6902756690979004, | |
| "learning_rate": 1.9644444444444447e-05, | |
| "loss": 0.062, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 3.2640000000000002, | |
| "grad_norm": 2.4366424083709717, | |
| "learning_rate": 1.9377777777777778e-05, | |
| "loss": 0.0552, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 3.288, | |
| "grad_norm": 0.8592342734336853, | |
| "learning_rate": 1.9111111111111113e-05, | |
| "loss": 0.0473, | |
| "step": 822 | |
| }, | |
| { | |
| "epoch": 3.312, | |
| "grad_norm": 0.7974979877471924, | |
| "learning_rate": 1.8844444444444444e-05, | |
| "loss": 0.0843, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 3.336, | |
| "grad_norm": 0.6507941484451294, | |
| "learning_rate": 1.8577777777777776e-05, | |
| "loss": 0.0547, | |
| "step": 834 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "grad_norm": 1.7816904783248901, | |
| "learning_rate": 1.8311111111111114e-05, | |
| "loss": 0.0734, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 3.384, | |
| "grad_norm": 2.3007311820983887, | |
| "learning_rate": 1.8044444444444445e-05, | |
| "loss": 0.1033, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 3.408, | |
| "grad_norm": 1.0759015083312988, | |
| "learning_rate": 1.777777777777778e-05, | |
| "loss": 0.0992, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 3.432, | |
| "grad_norm": 2.1372885704040527, | |
| "learning_rate": 1.751111111111111e-05, | |
| "loss": 0.0593, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 3.456, | |
| "grad_norm": 2.228823661804199, | |
| "learning_rate": 1.7244444444444446e-05, | |
| "loss": 0.0937, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "grad_norm": 1.4194374084472656, | |
| "learning_rate": 1.6977777777777777e-05, | |
| "loss": 0.0667, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 3.504, | |
| "grad_norm": 0.7095490097999573, | |
| "learning_rate": 1.6711111111111112e-05, | |
| "loss": 0.0574, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 3.528, | |
| "grad_norm": 3.3914129734039307, | |
| "learning_rate": 1.6444444444444447e-05, | |
| "loss": 0.0969, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 3.552, | |
| "grad_norm": 1.8268787860870361, | |
| "learning_rate": 1.617777777777778e-05, | |
| "loss": 0.0716, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 3.576, | |
| "grad_norm": 1.4750251770019531, | |
| "learning_rate": 1.5911111111111113e-05, | |
| "loss": 0.0859, | |
| "step": 894 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "grad_norm": 0.3522164523601532, | |
| "learning_rate": 1.5644444444444444e-05, | |
| "loss": 0.0505, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.624, | |
| "grad_norm": 1.7711290121078491, | |
| "learning_rate": 1.537777777777778e-05, | |
| "loss": 0.0571, | |
| "step": 906 | |
| }, | |
| { | |
| "epoch": 3.648, | |
| "grad_norm": 1.3283618688583374, | |
| "learning_rate": 1.5111111111111112e-05, | |
| "loss": 0.1006, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 3.672, | |
| "grad_norm": 2.121399402618408, | |
| "learning_rate": 1.4844444444444444e-05, | |
| "loss": 0.0838, | |
| "step": 918 | |
| }, | |
| { | |
| "epoch": 3.6959999999999997, | |
| "grad_norm": 2.0860633850097656, | |
| "learning_rate": 1.4577777777777778e-05, | |
| "loss": 0.1117, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 3.7199999999999998, | |
| "grad_norm": 2.2945892810821533, | |
| "learning_rate": 1.4311111111111111e-05, | |
| "loss": 0.0727, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 3.7439999999999998, | |
| "grad_norm": 1.119083046913147, | |
| "learning_rate": 1.4044444444444446e-05, | |
| "loss": 0.0485, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 3.768, | |
| "grad_norm": 1.8427727222442627, | |
| "learning_rate": 1.3777777777777778e-05, | |
| "loss": 0.0574, | |
| "step": 942 | |
| }, | |
| { | |
| "epoch": 3.792, | |
| "grad_norm": 1.5588749647140503, | |
| "learning_rate": 1.351111111111111e-05, | |
| "loss": 0.0784, | |
| "step": 948 | |
| }, | |
| { | |
| "epoch": 3.816, | |
| "grad_norm": 1.580621361732483, | |
| "learning_rate": 1.3244444444444445e-05, | |
| "loss": 0.054, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "grad_norm": 4.9234843254089355, | |
| "learning_rate": 1.2977777777777777e-05, | |
| "loss": 0.0976, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 3.864, | |
| "grad_norm": 1.1440095901489258, | |
| "learning_rate": 1.2711111111111113e-05, | |
| "loss": 0.0586, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 3.888, | |
| "grad_norm": 1.0315749645233154, | |
| "learning_rate": 1.2444444444444445e-05, | |
| "loss": 0.0693, | |
| "step": 972 | |
| }, | |
| { | |
| "epoch": 3.912, | |
| "grad_norm": 1.4318304061889648, | |
| "learning_rate": 1.2177777777777778e-05, | |
| "loss": 0.069, | |
| "step": 978 | |
| }, | |
| { | |
| "epoch": 3.936, | |
| "grad_norm": 2.342024087905884, | |
| "learning_rate": 1.1911111111111112e-05, | |
| "loss": 0.0815, | |
| "step": 984 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "grad_norm": 1.2760955095291138, | |
| "learning_rate": 1.1644444444444446e-05, | |
| "loss": 0.07, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 3.984, | |
| "grad_norm": 1.5678285360336304, | |
| "learning_rate": 1.1377777777777779e-05, | |
| "loss": 0.0795, | |
| "step": 996 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.943, | |
| "eval_f1_macro": 0.9169826832623412, | |
| "eval_f1_micro": 0.943, | |
| "eval_f1_weighted": 0.9427985114313238, | |
| "eval_loss": 0.13341853022575378, | |
| "eval_precision_macro": 0.9227534317185495, | |
| "eval_precision_micro": 0.943, | |
| "eval_precision_weighted": 0.9430912986498113, | |
| "eval_recall_macro": 0.9119580961776227, | |
| "eval_recall_micro": 0.943, | |
| "eval_recall_weighted": 0.943, | |
| "eval_runtime": 3.3617, | |
| "eval_samples_per_second": 594.941, | |
| "eval_steps_per_second": 4.76, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 6, | |
| "max_steps": 1250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 2 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4209928077312000.0, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |