{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 1.0, | |
"global_step": 732, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.4, | |
"learning_rate": 2.019756838905775e-05, | |
"loss": 0.1333, | |
"step": 292 | |
}, | |
{ | |
"epoch": 0.8, | |
"learning_rate": 6.884498480243161e-06, | |
"loss": 0.0543, | |
"step": 584 | |
} | |
], | |
"max_steps": 732, | |
"num_train_epochs": 1, | |
"total_flos": 1.815172407581737e+18, | |
"trial_name": null, | |
"trial_params": null | |
} | |