| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.3239669421487603, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 6.7247, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 3.472536087036133, | |
| "eval_runtime": 615.8884, | |
| "eval_samples_per_second": 3.553, | |
| "eval_wer": 1.0, | |
| "step": 400 | |
| } | |
| ], | |
| "max_steps": 3020, | |
| "num_train_epochs": 10, | |
| "total_flos": 8.196165988048397e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |