|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 5.0, |
|
"global_step": 685, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 7.82608695652174e-05, |
|
"loss": 1.5533, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 0.0001536231884057971, |
|
"loss": 1.3582, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 0.00019642857142857144, |
|
"loss": 1.32, |
|
"step": 81 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 0.00018766233766233769, |
|
"loss": 1.2552, |
|
"step": 108 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 0.0001788961038961039, |
|
"loss": 1.2336, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 0.00017012987012987013, |
|
"loss": 1.1885, |
|
"step": 162 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 0.00016136363636363635, |
|
"loss": 1.2022, |
|
"step": 189 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"learning_rate": 0.0001525974025974026, |
|
"loss": 1.1927, |
|
"step": 216 |
|
}, |
|
{ |
|
"epoch": 1.77, |
|
"learning_rate": 0.00014383116883116883, |
|
"loss": 1.1789, |
|
"step": 243 |
|
}, |
|
{ |
|
"epoch": 1.97, |
|
"learning_rate": 0.00013506493506493507, |
|
"loss": 1.1918, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 2.17, |
|
"learning_rate": 0.0001262987012987013, |
|
"loss": 1.1426, |
|
"step": 297 |
|
}, |
|
{ |
|
"epoch": 2.36, |
|
"learning_rate": 0.00011753246753246753, |
|
"loss": 1.1104, |
|
"step": 324 |
|
}, |
|
{ |
|
"epoch": 2.56, |
|
"learning_rate": 0.00010876623376623376, |
|
"loss": 1.148, |
|
"step": 351 |
|
}, |
|
{ |
|
"epoch": 2.76, |
|
"learning_rate": 0.0001, |
|
"loss": 1.1244, |
|
"step": 378 |
|
}, |
|
{ |
|
"epoch": 2.96, |
|
"learning_rate": 9.123376623376624e-05, |
|
"loss": 1.0997, |
|
"step": 405 |
|
}, |
|
{ |
|
"epoch": 3.15, |
|
"learning_rate": 8.246753246753248e-05, |
|
"loss": 1.0676, |
|
"step": 432 |
|
}, |
|
{ |
|
"epoch": 3.35, |
|
"learning_rate": 7.37012987012987e-05, |
|
"loss": 1.0429, |
|
"step": 459 |
|
}, |
|
{ |
|
"epoch": 3.55, |
|
"learning_rate": 6.493506493506494e-05, |
|
"loss": 1.0455, |
|
"step": 486 |
|
}, |
|
{ |
|
"epoch": 3.74, |
|
"learning_rate": 5.616883116883117e-05, |
|
"loss": 1.0255, |
|
"step": 513 |
|
}, |
|
{ |
|
"epoch": 3.94, |
|
"learning_rate": 4.740259740259741e-05, |
|
"loss": 1.0583, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 4.14, |
|
"learning_rate": 3.8636363636363636e-05, |
|
"loss": 1.0279, |
|
"step": 567 |
|
}, |
|
{ |
|
"epoch": 4.34, |
|
"learning_rate": 2.9870129870129872e-05, |
|
"loss": 0.9746, |
|
"step": 594 |
|
}, |
|
{ |
|
"epoch": 4.53, |
|
"learning_rate": 2.1103896103896105e-05, |
|
"loss": 0.9944, |
|
"step": 621 |
|
}, |
|
{ |
|
"epoch": 4.73, |
|
"learning_rate": 1.2337662337662339e-05, |
|
"loss": 0.9703, |
|
"step": 648 |
|
}, |
|
{ |
|
"epoch": 4.93, |
|
"learning_rate": 3.5714285714285714e-06, |
|
"loss": 0.9644, |
|
"step": 675 |
|
} |
|
], |
|
"max_steps": 685, |
|
"num_train_epochs": 5, |
|
"total_flos": 5.700380906225664e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|