{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 2.1508875739644973, | |
"eval_steps": 500, | |
"global_step": 153, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 1.05, | |
"learning_rate": 0.00012941176470588237, | |
"loss": 0.7567, | |
"step": 67 | |
}, | |
{ | |
"epoch": 2.09, | |
"learning_rate": 0.00019342105263157894, | |
"loss": 0.3919, | |
"step": 134 | |
} | |
], | |
"logging_steps": 67, | |
"max_steps": 1014, | |
"num_train_epochs": 3, | |
"save_steps": 500, | |
"total_flos": 6723675831140352.0, | |
"trial_name": null, | |
"trial_params": null | |
} | |