| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 30.0, | |
| "global_step": 840, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 17.86, | |
| "learning_rate": 2.023809523809524e-05, | |
| "loss": 1.8057, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "step": 840, | |
| "total_flos": 3103643652157440.0, | |
| "train_loss": 1.5763432820638021, | |
| "train_runtime": 801.7351, | |
| "train_samples_per_second": 4.153, | |
| "train_steps_per_second": 1.048 | |
| } | |
| ], | |
| "max_steps": 840, | |
| "num_train_epochs": 30, | |
| "total_flos": 3103643652157440.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |