| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "global_step": 1235, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.6016194331983808e-05, | |
| "loss": 0.4483, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7487179487179487, | |
| "eval_f1": 0.7487179487179487, | |
| "eval_loss": 0.4952045679092407, | |
| "eval_precision": 0.7647108119955648, | |
| "eval_recall": 0.7647108119955648, | |
| "eval_runtime": 8.7776, | |
| "eval_samples_per_second": 111.078, | |
| "eval_steps_per_second": 3.532, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.2032388663967612e-05, | |
| "loss": 0.3232, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7702564102564102, | |
| "eval_f1": 0.7689612565799495, | |
| "eval_loss": 0.4948658049106598, | |
| "eval_precision": 0.7698926993477804, | |
| "eval_recall": 0.7756504473840282, | |
| "eval_runtime": 8.808, | |
| "eval_samples_per_second": 110.695, | |
| "eval_steps_per_second": 3.52, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 8.048582995951418e-06, | |
| "loss": 0.2305, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7487179487179487, | |
| "eval_f1": 0.7484120071324076, | |
| "eval_loss": 0.6224679350852966, | |
| "eval_precision": 0.7555643946446404, | |
| "eval_recall": 0.7595600938603956, | |
| "eval_runtime": 8.8313, | |
| "eval_samples_per_second": 110.402, | |
| "eval_steps_per_second": 3.51, | |
| "step": 741 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 4.0647773279352235e-06, | |
| "loss": 0.1562, | |
| "step": 984 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7548717948717949, | |
| "eval_f1": 0.7543715590673024, | |
| "eval_loss": 0.7372676134109497, | |
| "eval_precision": 0.7595693678941904, | |
| "eval_recall": 0.7643304711069854, | |
| "eval_runtime": 8.9015, | |
| "eval_samples_per_second": 109.532, | |
| "eval_steps_per_second": 3.483, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 8.097165991902835e-08, | |
| "loss": 0.1069, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7538461538461538, | |
| "eval_f1": 0.7532728254268168, | |
| "eval_loss": 0.8184728026390076, | |
| "eval_precision": 0.7579311188339294, | |
| "eval_recall": 0.7628284469198834, | |
| "eval_runtime": 8.9703, | |
| "eval_samples_per_second": 108.692, | |
| "eval_steps_per_second": 3.456, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 1235, | |
| "total_flos": 5229150561945600.0, | |
| "train_loss": 0.2526789609237238, | |
| "train_runtime": 1072.8264, | |
| "train_samples_per_second": 36.795, | |
| "train_steps_per_second": 1.151 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7538461538461538, | |
| "eval_f1": 0.7532728254268168, | |
| "eval_loss": 0.8184728026390076, | |
| "eval_precision": 0.7579311188339294, | |
| "eval_recall": 0.7628284469198834, | |
| "eval_runtime": 10.0639, | |
| "eval_samples_per_second": 96.88, | |
| "eval_steps_per_second": 3.08, | |
| "step": 1235 | |
| } | |
| ], | |
| "max_steps": 1235, | |
| "num_train_epochs": 5, | |
| "total_flos": 5229150561945600.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |