{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 1.9991823385118561, | |
"global_step": 4890, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.2, | |
"learning_rate": 3e-05, | |
"loss": 0.2132, | |
"step": 500 | |
}, | |
{ | |
"epoch": 0.41, | |
"learning_rate": 2.6584699453551913e-05, | |
"loss": 0.0331, | |
"step": 1000 | |
}, | |
{ | |
"epoch": 0.61, | |
"learning_rate": 2.3169398907103826e-05, | |
"loss": 0.0277, | |
"step": 1500 | |
}, | |
{ | |
"epoch": 0.82, | |
"learning_rate": 1.975409836065574e-05, | |
"loss": 0.0269, | |
"step": 2000 | |
}, | |
{ | |
"epoch": 1.02, | |
"learning_rate": 1.633879781420765e-05, | |
"loss": 0.0261, | |
"step": 2500 | |
}, | |
{ | |
"epoch": 1.23, | |
"learning_rate": 1.2923497267759564e-05, | |
"loss": 0.0244, | |
"step": 3000 | |
}, | |
{ | |
"epoch": 1.43, | |
"learning_rate": 9.508196721311476e-06, | |
"loss": 0.0239, | |
"step": 3500 | |
}, | |
{ | |
"epoch": 1.64, | |
"learning_rate": 6.092896174863388e-06, | |
"loss": 0.0232, | |
"step": 4000 | |
}, | |
{ | |
"epoch": 1.84, | |
"learning_rate": 2.6775956284153005e-06, | |
"loss": 0.0234, | |
"step": 4500 | |
} | |
], | |
"max_steps": 4892, | |
"num_train_epochs": 2, | |
"total_flos": 4.238314825580544e+16, | |
"trial_name": null, | |
"trial_params": null | |
} | |