| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "global_step": 11815, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.9153618281845116e-05, | |
| "loss": 0.0365, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_EG_f1": 0.9898869720404521, | |
| "eval_ET_f1": 0.9967868618350589, | |
| "eval_TE_f1": 0.988691822402095, | |
| "eval_loss": 0.0057431175373494625, | |
| "eval_overall_accuracy": 0.998336295769641, | |
| "eval_overall_f1": 0.9917886469118172, | |
| "eval_overall_precision": 0.9914346895074947, | |
| "eval_overall_recall": 0.9921428571428571, | |
| "eval_runtime": 105.4808, | |
| "eval_samples_per_second": 39.818, | |
| "eval_steps_per_second": 2.493, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.8307236563690226e-05, | |
| "loss": 0.0079, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_EG_f1": 0.9944080904223678, | |
| "eval_ET_f1": 0.9988095238095238, | |
| "eval_TE_f1": 0.9936957297490187, | |
| "eval_loss": 0.003063528100028634, | |
| "eval_overall_accuracy": 0.9991894774262353, | |
| "eval_overall_f1": 0.9956369982547992, | |
| "eval_overall_precision": 0.995163336504916, | |
| "eval_overall_recall": 0.9961111111111111, | |
| "eval_runtime": 103.5359, | |
| "eval_samples_per_second": 40.566, | |
| "eval_steps_per_second": 2.54, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 1.7460854845535337e-05, | |
| "loss": 0.0043, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_EG_f1": 0.997381575815282, | |
| "eval_ET_f1": 0.9983337300642704, | |
| "eval_TE_f1": 0.9963073257891601, | |
| "eval_loss": 0.0027184109203517437, | |
| "eval_overall_accuracy": 0.999431212228937, | |
| "eval_overall_f1": 0.9973411643319179, | |
| "eval_overall_precision": 0.997380744503532, | |
| "eval_overall_recall": 0.9973015873015874, | |
| "eval_runtime": 102.7681, | |
| "eval_samples_per_second": 40.869, | |
| "eval_steps_per_second": 2.559, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 1.661447312738045e-05, | |
| "loss": 0.0021, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_EG_f1": 0.9942870745060699, | |
| "eval_ET_f1": 0.9983333333333333, | |
| "eval_TE_f1": 0.9942857142857143, | |
| "eval_loss": 0.00385509361512959, | |
| "eval_overall_accuracy": 0.9992179168147884, | |
| "eval_overall_f1": 0.9956352670422981, | |
| "eval_overall_precision": 0.9955562609109665, | |
| "eval_overall_recall": 0.9957142857142857, | |
| "eval_runtime": 103.0813, | |
| "eval_samples_per_second": 40.745, | |
| "eval_steps_per_second": 2.551, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 1.5768091409225562e-05, | |
| "loss": 0.002, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_EG_f1": 0.9958348208972985, | |
| "eval_ET_f1": 0.9990476190476191, | |
| "eval_TE_f1": 0.9957142857142857, | |
| "eval_loss": 0.0032494200859218836, | |
| "eval_overall_accuracy": 0.9993174546747245, | |
| "eval_overall_f1": 0.996865452525493, | |
| "eval_overall_precision": 0.9967468063159565, | |
| "eval_overall_recall": 0.996984126984127, | |
| "eval_runtime": 102.2205, | |
| "eval_samples_per_second": 41.088, | |
| "eval_steps_per_second": 2.573, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 1.4921709691070674e-05, | |
| "loss": 0.0013, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_EG_f1": 0.9952403617325083, | |
| "eval_ET_f1": 0.998928698964409, | |
| "eval_TE_f1": 0.994880342897964, | |
| "eval_loss": 0.003066167002543807, | |
| "eval_overall_accuracy": 0.9992605758976182, | |
| "eval_overall_f1": 0.9963497857482939, | |
| "eval_overall_precision": 0.9961916851793081, | |
| "eval_overall_recall": 0.9965079365079365, | |
| "eval_runtime": 102.0329, | |
| "eval_samples_per_second": 41.163, | |
| "eval_steps_per_second": 2.578, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 1.4075327972915787e-05, | |
| "loss": 0.002, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_EG_f1": 0.9971428571428571, | |
| "eval_ET_f1": 0.9990476190476191, | |
| "eval_TE_f1": 0.9971428571428571, | |
| "eval_loss": 0.00179725990165025, | |
| "eval_overall_accuracy": 0.9995591894774263, | |
| "eval_overall_f1": 0.9977777777777778, | |
| "eval_overall_precision": 0.9977777777777778, | |
| "eval_overall_recall": 0.9977777777777778, | |
| "eval_runtime": 104.5567, | |
| "eval_samples_per_second": 40.17, | |
| "eval_steps_per_second": 2.515, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 1.3228946254760899e-05, | |
| "loss": 0.0009, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "eval_EG_f1": 0.9976196143775291, | |
| "eval_ET_f1": 0.998690632067611, | |
| "eval_TE_f1": 0.996904761904762, | |
| "eval_loss": 0.0014693811535835266, | |
| "eval_overall_accuracy": 0.999701386420192, | |
| "eval_overall_f1": 0.9977383644804191, | |
| "eval_overall_precision": 0.9976196143775291, | |
| "eval_overall_recall": 0.9978571428571429, | |
| "eval_runtime": 102.0191, | |
| "eval_samples_per_second": 41.169, | |
| "eval_steps_per_second": 2.578, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 1.238256453660601e-05, | |
| "loss": 0.0008, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "eval_EG_f1": 0.997381575815282, | |
| "eval_ET_f1": 0.9992857142857143, | |
| "eval_TE_f1": 0.9973809523809524, | |
| "eval_loss": 0.0014952768106013536, | |
| "eval_overall_accuracy": 0.9997298258087451, | |
| "eval_overall_f1": 0.998016030473772, | |
| "eval_overall_precision": 0.9979368354229488, | |
| "eval_overall_recall": 0.9980952380952381, | |
| "eval_runtime": 102.1451, | |
| "eval_samples_per_second": 41.118, | |
| "eval_steps_per_second": 2.575, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 1.1536182818451122e-05, | |
| "loss": 0.0008, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "eval_EG_f1": 0.9976190476190476, | |
| "eval_ET_f1": 0.9983333333333333, | |
| "eval_TE_f1": 0.9972615787593762, | |
| "eval_loss": 0.00143534317612648, | |
| "eval_overall_accuracy": 0.9997298258087451, | |
| "eval_overall_f1": 0.9977380054764079, | |
| "eval_overall_precision": 0.9977776013969363, | |
| "eval_overall_recall": 0.9976984126984128, | |
| "eval_runtime": 103.0577, | |
| "eval_samples_per_second": 40.754, | |
| "eval_steps_per_second": 2.552, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 1.0689801100296236e-05, | |
| "loss": 0.0005, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "eval_EG_f1": 0.9974997023455173, | |
| "eval_ET_f1": 0.9995238095238095, | |
| "eval_TE_f1": 0.9973809523809524, | |
| "eval_loss": 0.0019883255008608103, | |
| "eval_overall_accuracy": 0.9996729470316388, | |
| "eval_overall_f1": 0.9981348466208977, | |
| "eval_overall_precision": 0.9981744582903405, | |
| "eval_overall_recall": 0.9980952380952381, | |
| "eval_runtime": 102.2987, | |
| "eval_samples_per_second": 41.056, | |
| "eval_steps_per_second": 2.571, | |
| "step": 11000 | |
| } | |
| ], | |
| "max_steps": 23630, | |
| "num_train_epochs": 10, | |
| "total_flos": 2874592437250464.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |