| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 21.62162162162162, | |
| "global_step": 800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 10.81, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 4.9403, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 10.81, | |
| "eval_loss": 1.2926115989685059, | |
| "eval_runtime": 137.3484, | |
| "eval_samples_per_second": 3.393, | |
| "eval_wer": 0.9984797810884768, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 21.62, | |
| "learning_rate": 0.00015245901639344262, | |
| "loss": 0.3873, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 21.62, | |
| "eval_loss": 0.6025914549827576, | |
| "eval_runtime": 137.9933, | |
| "eval_samples_per_second": 3.377, | |
| "eval_wer": 0.7062937062937062, | |
| "step": 800 | |
| } | |
| ], | |
| "max_steps": 1110, | |
| "num_train_epochs": 30, | |
| "total_flos": 3.851482463327324e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |