| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.202643171806167, |
| "global_step": 500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 2.2, |
| "learning_rate": 0.000495, |
| "loss": 9.8739, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.2, |
| "eval_loss": 2.894528388977051, |
| "eval_runtime": 15.8125, |
| "eval_samples_per_second": 32.759, |
| "eval_steps_per_second": 8.221, |
| "eval_wer": 0.9981308411214953, |
| "step": 500 |
| } |
| ], |
| "max_steps": 681, |
| "num_train_epochs": 3, |
| "total_flos": 5.864898206663059e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
