{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 1.0, | |
"global_step": 204, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.2, | |
"learning_rate": 0.0002688524590163934, | |
"loss": 0.0, | |
"step": 40 | |
}, | |
{ | |
"epoch": 0.39, | |
"learning_rate": 0.00020327868852459014, | |
"loss": 0.0, | |
"step": 80 | |
}, | |
{ | |
"epoch": 0.59, | |
"learning_rate": 0.00013770491803278688, | |
"loss": 0.0, | |
"step": 120 | |
}, | |
{ | |
"epoch": 0.78, | |
"learning_rate": 7.21311475409836e-05, | |
"loss": 0.0, | |
"step": 160 | |
}, | |
{ | |
"epoch": 0.98, | |
"learning_rate": 6.5573770491803276e-06, | |
"loss": 0.0, | |
"step": 200 | |
} | |
], | |
"max_steps": 204, | |
"num_train_epochs": 1, | |
"total_flos": 1.456536337514496e+16, | |
"trial_name": null, | |
"trial_params": null | |
} | |