| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.785894206549118, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 0.00039436231366470835, | |
| "loss": 1.5121, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "eval_loss": 0.186998650431633, | |
| "eval_runtime": 714.138, | |
| "eval_samples_per_second": 7.242, | |
| "eval_wer": 0.39502654080485317, | |
| "step": 500 | |
| } | |
| ], | |
| "max_steps": 6600, | |
| "num_train_epochs": 50, | |
| "total_flos": 7.843188479774457e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |