| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 100.0, | |
| "global_step": 700, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 71.43, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 1.119, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 700, | |
| "total_flos": 731617689600000.0, | |
| "train_loss": 0.858495488848005, | |
| "train_runtime": 1306.0127, | |
| "train_samples_per_second": 1.072, | |
| "train_steps_per_second": 0.536 | |
| } | |
| ], | |
| "max_steps": 700, | |
| "num_train_epochs": 100, | |
| "total_flos": 731617689600000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |