| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 1254, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.0063795853269537e-05, | |
| "loss": 4.6872, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.0127591706539077e-05, | |
| "loss": 4.0076, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 1254, | |
| "total_flos": 2635829619333120.0, | |
| "train_loss": 4.2545356324605015, | |
| "train_runtime": 243.0064, | |
| "train_samples_per_second": 41.221, | |
| "train_steps_per_second": 5.16 | |
| } | |
| ], | |
| "max_steps": 1254, | |
| "num_train_epochs": 3, | |
| "total_flos": 2635829619333120.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |