| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 1224, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 2.957516339869281e-05, | |
| "loss": 2.9635, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 9.150326797385621e-06, | |
| "loss": 1.8815, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 1224, | |
| "total_flos": 1886383299379200.0, | |
| "train_loss": 2.2662667417837903, | |
| "train_runtime": 330.08, | |
| "train_samples_per_second": 37.036, | |
| "train_steps_per_second": 3.708 | |
| } | |
| ], | |
| "max_steps": 1224, | |
| "num_train_epochs": 3, | |
| "total_flos": 1886383299379200.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |