| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "global_step": 2190, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.009132420091326e-05, | |
| "loss": 0.2106, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9639948564080583, | |
| "eval_f1": 0.9653751030502885, | |
| "eval_loss": 0.11960607767105103, | |
| "eval_precision": 0.9653751030502885, | |
| "eval_recall": 0.9653751030502885, | |
| "eval_roc_auc": 0.9639375515251443, | |
| "eval_runtime": 7.2687, | |
| "eval_samples_per_second": 962.897, | |
| "eval_steps_per_second": 7.567, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.009132420091324e-05, | |
| "loss": 0.086, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9735676525217888, | |
| "eval_f1": 0.9742805505352425, | |
| "eval_loss": 0.08830533176660538, | |
| "eval_precision": 0.9859313449634215, | |
| "eval_recall": 0.9629018961253092, | |
| "eval_roc_auc": 0.9740104718721784, | |
| "eval_runtime": 7.2659, | |
| "eval_samples_per_second": 963.269, | |
| "eval_steps_per_second": 7.57, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.009132420091324e-05, | |
| "loss": 0.0477, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9728532647521074, | |
| "eval_f1": 0.9737931034482759, | |
| "eval_loss": 0.09442037343978882, | |
| "eval_precision": 0.977568540570479, | |
| "eval_recall": 0.9700467161308052, | |
| "eval_roc_auc": 0.9729697866368312, | |
| "eval_runtime": 7.2693, | |
| "eval_samples_per_second": 962.82, | |
| "eval_steps_per_second": 7.566, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 6.0091324200913244e-05, | |
| "loss": 0.0269, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9722817545363623, | |
| "eval_f1": 0.9734246575342465, | |
| "eval_loss": 0.12147631496191025, | |
| "eval_precision": 0.9704998634252936, | |
| "eval_recall": 0.9763671338279747, | |
| "eval_roc_auc": 0.9721121383425587, | |
| "eval_runtime": 7.2591, | |
| "eval_samples_per_second": 964.173, | |
| "eval_steps_per_second": 7.577, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 5.0091324200913245e-05, | |
| "loss": 0.0146, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9742820402914703, | |
| "eval_f1": 0.9750069425159679, | |
| "eval_loss": 0.12991154193878174, | |
| "eval_precision": 0.9854055571147909, | |
| "eval_recall": 0.9648255015114042, | |
| "eval_roc_auc": 0.9746746555176069, | |
| "eval_runtime": 7.2686, | |
| "eval_samples_per_second": 962.904, | |
| "eval_steps_per_second": 7.567, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.0091324200913246e-05, | |
| "loss": 0.0069, | |
| "step": 1314 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9749964280611516, | |
| "eval_f1": 0.9758187094099765, | |
| "eval_loss": 0.15036572515964508, | |
| "eval_precision": 0.9813785436353529, | |
| "eval_recall": 0.9703215169002474, | |
| "eval_roc_auc": 0.9751905203548855, | |
| "eval_runtime": 7.2605, | |
| "eval_samples_per_second": 963.989, | |
| "eval_steps_per_second": 7.575, | |
| "step": 1314 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.0091324200913247e-05, | |
| "loss": 0.0044, | |
| "step": 1533 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9742820402914703, | |
| "eval_f1": 0.9751997795535962, | |
| "eval_loss": 0.16526658833026886, | |
| "eval_precision": 0.9778944459795523, | |
| "eval_recall": 0.9725199230557846, | |
| "eval_roc_auc": 0.9743551996231304, | |
| "eval_runtime": 7.2696, | |
| "eval_samples_per_second": 962.776, | |
| "eval_steps_per_second": 7.566, | |
| "step": 1533 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2.009132420091324e-05, | |
| "loss": 0.0019, | |
| "step": 1752 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9755679382768967, | |
| "eval_f1": 0.9763779527559054, | |
| "eval_loss": 0.18039505183696747, | |
| "eval_precision": 0.9816666666666667, | |
| "eval_recall": 0.9711459192085737, | |
| "eval_roc_auc": 0.9757515310328582, | |
| "eval_runtime": 7.2685, | |
| "eval_samples_per_second": 962.918, | |
| "eval_steps_per_second": 7.567, | |
| "step": 1752 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 1.0091324200913242e-05, | |
| "loss": 0.0008, | |
| "step": 1971 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9767109587083869, | |
| "eval_f1": 0.9774581662287374, | |
| "eval_loss": 0.18273666501045227, | |
| "eval_precision": 0.9838530066815144, | |
| "eval_recall": 0.9711459192085737, | |
| "eval_roc_auc": 0.9769420072233344, | |
| "eval_runtime": 7.2614, | |
| "eval_samples_per_second": 963.859, | |
| "eval_steps_per_second": 7.574, | |
| "step": 1971 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 9.132420091324201e-08, | |
| "loss": 0.0008, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9769967138162595, | |
| "eval_f1": 0.9777347531461762, | |
| "eval_loss": 0.17970030009746552, | |
| "eval_precision": 0.98413140311804, | |
| "eval_recall": 0.9714207199780159, | |
| "eval_roc_auc": 0.977228217131865, | |
| "eval_runtime": 7.262, | |
| "eval_samples_per_second": 963.777, | |
| "eval_steps_per_second": 7.574, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 2190, | |
| "total_flos": 3.68250233081856e+16, | |
| "train_loss": 0.040063528825431106, | |
| "train_runtime": 1111.3299, | |
| "train_samples_per_second": 251.878, | |
| "train_steps_per_second": 1.971 | |
| } | |
| ], | |
| "max_steps": 2190, | |
| "num_train_epochs": 10, | |
| "total_flos": 3.68250233081856e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |