| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "global_step": 126, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.57, |
| "learning_rate": 4.9206349206349204e-05, |
| "loss": 0.2872, |
| "step": 66 |
| }, |
| { |
| "epoch": 1.57, |
| "eval_accuracy": 0.9176646706586826, |
| "eval_f1": 0.9374999999999999, |
| "eval_loss": 0.20166487991809845, |
| "eval_precision": 0.9439359267734554, |
| "eval_recall": 0.9311512415349887, |
| "eval_roc_auc": 0.9111311763230499, |
| "eval_runtime": 1.9771, |
| "eval_samples_per_second": 675.722, |
| "eval_steps_per_second": 5.564, |
| "step": 66 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 126, |
| "total_flos": 2108308886599680.0, |
| "train_loss": 0.19368775685628256, |
| "train_runtime": 134.498, |
| "train_samples_per_second": 119.154, |
| "train_steps_per_second": 0.937 |
| } |
| ], |
| "max_steps": 126, |
| "num_train_epochs": 3, |
| "total_flos": 2108308886599680.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
