{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 2.4235632183908047, | |
"eval_steps": 500, | |
"global_step": 2211, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.2, | |
"learning_rate": 0.00013295019157088123, | |
"loss": 0.9293, | |
"step": 347 | |
}, | |
{ | |
"epoch": 0.4, | |
"learning_rate": 0.00019267773520647086, | |
"loss": 0.8681, | |
"step": 694 | |
}, | |
{ | |
"epoch": 1.17, | |
"learning_rate": 0.00017790549169859515, | |
"loss": 0.833, | |
"step": 1041 | |
}, | |
{ | |
"epoch": 1.37, | |
"learning_rate": 0.00016313324819071948, | |
"loss": 0.8007, | |
"step": 1388 | |
}, | |
{ | |
"epoch": 2.15, | |
"learning_rate": 0.00014836100468284378, | |
"loss": 0.7774, | |
"step": 1735 | |
}, | |
{ | |
"epoch": 2.35, | |
"learning_rate": 0.00013358876117496808, | |
"loss": 0.7542, | |
"step": 2082 | |
} | |
], | |
"logging_steps": 347, | |
"max_steps": 5220, | |
"num_train_epochs": 3, | |
"save_steps": 500, | |
"total_flos": 1.5451477483349606e+18, | |
"trial_name": null, | |
"trial_params": null | |
} | |