|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 30.0, |
|
"global_step": 5220, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 2.87, |
|
"learning_rate": 4.5210727969348656e-05, |
|
"loss": 0.3899, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 5.75, |
|
"learning_rate": 4.0421455938697324e-05, |
|
"loss": 0.0535, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 8.62, |
|
"learning_rate": 3.563218390804598e-05, |
|
"loss": 0.028, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 11.49, |
|
"learning_rate": 3.084291187739464e-05, |
|
"loss": 0.0164, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 14.37, |
|
"learning_rate": 2.6053639846743293e-05, |
|
"loss": 0.0107, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 17.24, |
|
"learning_rate": 2.1264367816091954e-05, |
|
"loss": 0.0076, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 20.11, |
|
"learning_rate": 1.6475095785440615e-05, |
|
"loss": 0.0055, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 22.99, |
|
"learning_rate": 1.1685823754789272e-05, |
|
"loss": 0.0043, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 25.86, |
|
"learning_rate": 6.896551724137932e-06, |
|
"loss": 0.0034, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 28.74, |
|
"learning_rate": 2.1072796934865904e-06, |
|
"loss": 0.0029, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 30.0, |
|
"step": 5220, |
|
"total_flos": 6.524183596345344e+16, |
|
"train_loss": 0.05012281981236177, |
|
"train_runtime": 3936.4674, |
|
"train_samples_per_second": 63.422, |
|
"train_steps_per_second": 1.326 |
|
} |
|
], |
|
"max_steps": 5220, |
|
"num_train_epochs": 30, |
|
"total_flos": 6.524183596345344e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|