| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 855, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.75, |
| "learning_rate": 2.0760233918128656e-05, |
| "loss": 3.3775, |
| "step": 500 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 855, |
| "total_flos": 1052093140588800.0, |
| "train_loss": 3.2651999668768275, |
| "train_runtime": 489.765, |
| "train_samples_per_second": 13.929, |
| "train_steps_per_second": 1.746 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 855, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "total_flos": 1052093140588800.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
