{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 2.23, | |
"eval_steps": 500, | |
"global_step": 69, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.2, | |
"learning_rate": 0.00013333333333333334, | |
"loss": 1.5566, | |
"step": 20 | |
}, | |
{ | |
"epoch": 1.17, | |
"learning_rate": 0.0001925925925925926, | |
"loss": 1.389, | |
"step": 40 | |
}, | |
{ | |
"epoch": 2.14, | |
"learning_rate": 0.00017777777777777779, | |
"loss": 1.2155, | |
"step": 60 | |
} | |
], | |
"logging_steps": 20, | |
"max_steps": 300, | |
"num_train_epochs": 3, | |
"save_steps": 500, | |
"total_flos": 1.1218588224454656e+16, | |
"trial_name": null, | |
"trial_params": null | |
} | |