| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.297029702970297, | |
| "global_step": 800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 6.8625, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "eval_loss": 3.4594738483428955, | |
| "eval_runtime": 211.356, | |
| "eval_samples_per_second": 10.352, | |
| "eval_wer": 1.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 7.832512315270935e-05, | |
| "loss": 1.5787, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "eval_loss": 0.6689605116844177, | |
| "eval_runtime": 220.0088, | |
| "eval_samples_per_second": 9.945, | |
| "eval_wer": 0.6838202674440712, | |
| "step": 800 | |
| } | |
| ], | |
| "max_steps": 906, | |
| "num_train_epochs": 6, | |
| "total_flos": 3.298739982613021e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |