{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 100.0, | |
"global_step": 100, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 50.0, | |
"learning_rate": 2e-05, | |
"loss": 1.7188, | |
"step": 50 | |
}, | |
{ | |
"epoch": 100.0, | |
"learning_rate": 2e-05, | |
"loss": 1.0563, | |
"step": 100 | |
} | |
], | |
"max_steps": 100, | |
"num_train_epochs": 100, | |
"total_flos": 2.2117827698688e+16, | |
"trial_name": null, | |
"trial_params": null | |
} | |