|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.857142857142857, |
|
"eval_steps": 500, |
|
"global_step": 8000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0898, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 4.683544303797468e-05, |
|
"loss": 0.0637, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 4.367088607594937e-05, |
|
"loss": 0.0706, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 4.050632911392405e-05, |
|
"loss": 0.0894, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 3.7341772151898736e-05, |
|
"loss": 0.1138, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 3.4177215189873416e-05, |
|
"loss": 0.1484, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 3.10126582278481e-05, |
|
"loss": 0.1201, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 2.7848101265822786e-05, |
|
"loss": 0.1216, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 1.61, |
|
"learning_rate": 2.468354430379747e-05, |
|
"loss": 0.1238, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 1.79, |
|
"learning_rate": 2.1518987341772153e-05, |
|
"loss": 0.1255, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 1.96, |
|
"learning_rate": 1.8354430379746836e-05, |
|
"loss": 0.1305, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 2.14, |
|
"learning_rate": 1.5189873417721521e-05, |
|
"loss": 0.1012, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 2.32, |
|
"learning_rate": 1.2025316455696203e-05, |
|
"loss": 0.0969, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"learning_rate": 8.860759493670886e-06, |
|
"loss": 0.1036, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 2.68, |
|
"learning_rate": 5.69620253164557e-06, |
|
"loss": 0.1146, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 2.86, |
|
"learning_rate": 2.531645569620253e-06, |
|
"loss": 0.1198, |
|
"step": 8000 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 8400, |
|
"num_train_epochs": 3, |
|
"save_steps": 500, |
|
"total_flos": 3.4673673633792e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|