|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 10.0, |
|
"global_step": 4170, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 4.991324875275794e-05, |
|
"loss": 2.3265, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 2.4, |
|
"learning_rate": 4.69397052278032e-05, |
|
"loss": 0.9988, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 3.6, |
|
"learning_rate": 4.021214822246739e-05, |
|
"loss": 0.5942, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 4.8, |
|
"learning_rate": 3.088170257757369e-05, |
|
"loss": 0.3763, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"learning_rate": 2.054486279317156e-05, |
|
"loss": 0.2525, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 7.19, |
|
"learning_rate": 1.0970323365940444e-05, |
|
"loss": 0.1775, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 8.39, |
|
"learning_rate": 3.7963446874883848e-06, |
|
"loss": 0.1421, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 9.59, |
|
"learning_rate": 2.504369903934739e-07, |
|
"loss": 0.1256, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"step": 4170, |
|
"total_flos": 3.505921644059904e+16, |
|
"train_loss": 0.6037493255212725, |
|
"train_runtime": 5563.3864, |
|
"train_samples_per_second": 8.987, |
|
"train_steps_per_second": 0.75 |
|
} |
|
], |
|
"max_steps": 4170, |
|
"num_train_epochs": 10, |
|
"total_flos": 3.505921644059904e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|