| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 630, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 1.0317460317460318e-05, | |
| "loss": 1.67, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 630, | |
| "total_flos": 1213271836262400.0, | |
| "train_loss": 1.5693510025266617, | |
| "train_runtime": 188.5122, | |
| "train_samples_per_second": 33.42, | |
| "train_steps_per_second": 3.342 | |
| } | |
| ], | |
| "max_steps": 630, | |
| "num_train_epochs": 3, | |
| "total_flos": 1213271836262400.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |