{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 19.649122807017545, | |
"eval_steps": 500, | |
"global_step": 560, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 3.16, | |
"learning_rate": 0.0009325396825396826, | |
"loss": 1.7533, | |
"step": 90 | |
}, | |
{ | |
"epoch": 6.32, | |
"learning_rate": 0.000753968253968254, | |
"loss": 1.6016, | |
"step": 180 | |
}, | |
{ | |
"epoch": 9.47, | |
"learning_rate": 0.0005753968253968254, | |
"loss": 1.5169, | |
"step": 270 | |
}, | |
{ | |
"epoch": 12.63, | |
"learning_rate": 0.0003968253968253968, | |
"loss": 1.4522, | |
"step": 360 | |
}, | |
{ | |
"epoch": 15.79, | |
"learning_rate": 0.00021825396825396825, | |
"loss": 1.3999, | |
"step": 450 | |
}, | |
{ | |
"epoch": 18.95, | |
"learning_rate": 3.968253968253968e-05, | |
"loss": 1.3576, | |
"step": 540 | |
} | |
], | |
"logging_steps": 90, | |
"max_steps": 560, | |
"num_train_epochs": 20, | |
"save_steps": 500, | |
"total_flos": 6.269099897434145e+18, | |
"trial_name": null, | |
"trial_params": null | |
} | |