| { | |
| "best_metric": 0.15928590297698975, | |
| "best_model_checkpoint": "./output4/checkpoint-512", | |
| "epoch": 4.6413597733711045, | |
| "global_step": 512, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.3914, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.3829, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.2e-05, | |
| "loss": 1.3398, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 1.0594, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_accuracy": 0.8646052631578948, | |
| "eval_f1": 0.8637236213946768, | |
| "eval_loss": 0.6905946731567383, | |
| "eval_precision": 0.8650720213650118, | |
| "eval_recall": 0.8646052631578948, | |
| "eval_runtime": 27.1686, | |
| "eval_samples_per_second": 279.735, | |
| "eval_steps_per_second": 4.122, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5565, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.3452, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 0.2851, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.2791, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_accuracy": 0.9181578947368421, | |
| "eval_f1": 0.9178446745855575, | |
| "eval_loss": 0.2583260238170624, | |
| "eval_precision": 0.9178522458398034, | |
| "eval_recall": 0.9181578947368422, | |
| "eval_runtime": 27.1489, | |
| "eval_samples_per_second": 279.938, | |
| "eval_steps_per_second": 4.125, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.2591, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 4e-05, | |
| "loss": 0.2432, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.2259, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.2263, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_accuracy": 0.9243421052631579, | |
| "eval_f1": 0.9244165095066339, | |
| "eval_loss": 0.21840104460716248, | |
| "eval_precision": 0.9274635904725687, | |
| "eval_recall": 0.924342105263158, | |
| "eval_runtime": 27.1511, | |
| "eval_samples_per_second": 279.915, | |
| "eval_steps_per_second": 4.125, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 4.955555555555556e-05, | |
| "loss": 0.2172, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 4.866666666666667e-05, | |
| "loss": 0.1923, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 4.7777777777777784e-05, | |
| "loss": 0.1875, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 4.6888888888888895e-05, | |
| "loss": 0.1826, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_accuracy": 0.9380263157894737, | |
| "eval_f1": 0.9380307153953753, | |
| "eval_loss": 0.18940293788909912, | |
| "eval_precision": 0.9385987876450141, | |
| "eval_recall": 0.9380263157894737, | |
| "eval_runtime": 27.4492, | |
| "eval_samples_per_second": 276.876, | |
| "eval_steps_per_second": 4.08, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 0.1835, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 4.511111111111112e-05, | |
| "loss": 0.1637, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 4.422222222222222e-05, | |
| "loss": 0.1598, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 0.1828, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_accuracy": 0.9384210526315789, | |
| "eval_f1": 0.9381955707045027, | |
| "eval_loss": 0.18510125577449799, | |
| "eval_precision": 0.9406898302033526, | |
| "eval_recall": 0.9384210526315789, | |
| "eval_runtime": 27.1424, | |
| "eval_samples_per_second": 280.004, | |
| "eval_steps_per_second": 4.126, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 4.2444444444444445e-05, | |
| "loss": 0.1722, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.155555555555556e-05, | |
| "loss": 0.1674, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 4.066666666666667e-05, | |
| "loss": 0.1678, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 3.977777777777778e-05, | |
| "loss": 0.1608, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_accuracy": 0.9396052631578947, | |
| "eval_f1": 0.939515727059736, | |
| "eval_loss": 0.17982347309589386, | |
| "eval_precision": 0.9416077079782574, | |
| "eval_recall": 0.9396052631578948, | |
| "eval_runtime": 27.1356, | |
| "eval_samples_per_second": 280.075, | |
| "eval_steps_per_second": 4.127, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.1697, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 3.8e-05, | |
| "loss": 0.1728, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 3.7111111111111113e-05, | |
| "loss": 0.1718, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 3.6222222222222225e-05, | |
| "loss": 0.1502, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_accuracy": 0.9496052631578947, | |
| "eval_f1": 0.9496119126383771, | |
| "eval_loss": 0.15795519948005676, | |
| "eval_precision": 0.9496711091764023, | |
| "eval_recall": 0.9496052631578947, | |
| "eval_runtime": 27.1505, | |
| "eval_samples_per_second": 279.921, | |
| "eval_steps_per_second": 4.125, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 3.5333333333333336e-05, | |
| "loss": 0.1359, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 3.444444444444445e-05, | |
| "loss": 0.1343, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 3.355555555555556e-05, | |
| "loss": 0.1199, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 3.266666666666667e-05, | |
| "loss": 0.1424, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_accuracy": 0.9465789473684211, | |
| "eval_f1": 0.9465467539090038, | |
| "eval_loss": 0.15993377566337585, | |
| "eval_precision": 0.9471187943151717, | |
| "eval_recall": 0.9465789473684211, | |
| "eval_runtime": 27.1331, | |
| "eval_samples_per_second": 280.1, | |
| "eval_steps_per_second": 4.128, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 3.177777777777778e-05, | |
| "loss": 0.1245, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 3.088888888888889e-05, | |
| "loss": 0.1314, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1301, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 2.9111111111111112e-05, | |
| "loss": 0.1383, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "eval_accuracy": 0.9456578947368421, | |
| "eval_f1": 0.94558793989311, | |
| "eval_loss": 0.16593697667121887, | |
| "eval_precision": 0.9469255477230607, | |
| "eval_recall": 0.9456578947368421, | |
| "eval_runtime": 27.1781, | |
| "eval_samples_per_second": 279.637, | |
| "eval_steps_per_second": 4.121, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 2.8222222222222223e-05, | |
| "loss": 0.143, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 2.733333333333333e-05, | |
| "loss": 0.1273, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 2.6444444444444443e-05, | |
| "loss": 0.1208, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 2.5555555555555554e-05, | |
| "loss": 0.1235, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_accuracy": 0.9478947368421052, | |
| "eval_f1": 0.947742882839795, | |
| "eval_loss": 0.16203150153160095, | |
| "eval_precision": 0.9479819938629999, | |
| "eval_recall": 0.9478947368421052, | |
| "eval_runtime": 27.1639, | |
| "eval_samples_per_second": 279.783, | |
| "eval_steps_per_second": 4.123, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 2.466666666666667e-05, | |
| "loss": 0.1358, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 2.377777777777778e-05, | |
| "loss": 0.1202, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 2.288888888888889e-05, | |
| "loss": 0.1095, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 0.0992, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "eval_accuracy": 0.9488157894736842, | |
| "eval_f1": 0.9486994674641721, | |
| "eval_loss": 0.1663181036710739, | |
| "eval_precision": 0.9488005469862106, | |
| "eval_recall": 0.9488157894736843, | |
| "eval_runtime": 27.1653, | |
| "eval_samples_per_second": 279.768, | |
| "eval_steps_per_second": 4.123, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 2.111111111111111e-05, | |
| "loss": 0.1007, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 2.0222222222222222e-05, | |
| "loss": 0.0977, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 1.9333333333333333e-05, | |
| "loss": 0.1016, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 1.8444444444444445e-05, | |
| "loss": 0.1066, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "eval_accuracy": 0.9498684210526316, | |
| "eval_f1": 0.949775085232258, | |
| "eval_loss": 0.16165488958358765, | |
| "eval_precision": 0.9500336429691177, | |
| "eval_recall": 0.9498684210526316, | |
| "eval_runtime": 27.1538, | |
| "eval_samples_per_second": 279.887, | |
| "eval_steps_per_second": 4.125, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 1.7555555555555556e-05, | |
| "loss": 0.1096, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.1028, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 1.577777777777778e-05, | |
| "loss": 0.1054, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 1.4888888888888888e-05, | |
| "loss": 0.0982, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "eval_accuracy": 0.9485526315789473, | |
| "eval_f1": 0.9484327367127127, | |
| "eval_loss": 0.161124125123024, | |
| "eval_precision": 0.9491280462351354, | |
| "eval_recall": 0.9485526315789473, | |
| "eval_runtime": 27.1519, | |
| "eval_samples_per_second": 279.907, | |
| "eval_steps_per_second": 4.125, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 0.1051, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 1.3111111111111113e-05, | |
| "loss": 0.1051, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 1.2222222222222222e-05, | |
| "loss": 0.1041, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 1.1333333333333334e-05, | |
| "loss": 0.0887, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "eval_accuracy": 0.9506578947368421, | |
| "eval_f1": 0.9505658100077847, | |
| "eval_loss": 0.15977711975574493, | |
| "eval_precision": 0.9508508453699076, | |
| "eval_recall": 0.9506578947368421, | |
| "eval_runtime": 27.1343, | |
| "eval_samples_per_second": 280.089, | |
| "eval_steps_per_second": 4.128, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 1.0444444444444445e-05, | |
| "loss": 0.0778, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 9.555555555555556e-06, | |
| "loss": 0.0858, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 8.666666666666668e-06, | |
| "loss": 0.0872, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 7.777777777777777e-06, | |
| "loss": 0.0891, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "eval_accuracy": 0.9511842105263157, | |
| "eval_f1": 0.9511326895081746, | |
| "eval_loss": 0.16269291937351227, | |
| "eval_precision": 0.9510882932907387, | |
| "eval_recall": 0.9511842105263157, | |
| "eval_runtime": 27.0255, | |
| "eval_samples_per_second": 281.216, | |
| "eval_steps_per_second": 4.144, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 6.888888888888889e-06, | |
| "loss": 0.0887, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0867, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 5.1111111111111115e-06, | |
| "loss": 0.091, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 4.222222222222223e-06, | |
| "loss": 0.0802, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "eval_accuracy": 0.950921052631579, | |
| "eval_f1": 0.9509254806694175, | |
| "eval_loss": 0.15928590297698975, | |
| "eval_precision": 0.9511139611391479, | |
| "eval_recall": 0.9509210526315789, | |
| "eval_runtime": 27.0214, | |
| "eval_samples_per_second": 281.259, | |
| "eval_steps_per_second": 4.145, | |
| "step": 512 | |
| } | |
| ], | |
| "max_steps": 550, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.465491747347497e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |