{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 0.5105296745373324, | |
"global_step": 400, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.51, | |
"learning_rate": 0.0002394, | |
"loss": 0.1243, | |
"step": 400 | |
}, | |
{ | |
"epoch": 0.51, | |
"eval_loss": 0.4312155246734619, | |
"eval_runtime": 1056.0895, | |
"eval_samples_per_second": 7.896, | |
"eval_steps_per_second": 0.988, | |
"eval_wer": 0.4201938721726975, | |
"step": 400 | |
} | |
], | |
"max_steps": 2349, | |
"num_train_epochs": 3, | |
"total_flos": 1.386778113240146e+18, | |
"trial_name": null, | |
"trial_params": null | |
} | |