|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 10.0, |
|
"global_step": 3510, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 1.7150997150997152e-05, |
|
"loss": 0.287, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 2.85, |
|
"learning_rate": 1.4301994301994305e-05, |
|
"loss": 0.157, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 4.27, |
|
"learning_rate": 1.1452991452991454e-05, |
|
"loss": 0.0685, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 5.7, |
|
"learning_rate": 8.603988603988605e-06, |
|
"loss": 0.0477, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 7.12, |
|
"learning_rate": 5.7549857549857555e-06, |
|
"loss": 0.0332, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 8.55, |
|
"learning_rate": 2.9059829059829063e-06, |
|
"loss": 0.0257, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 9.97, |
|
"learning_rate": 5.6980056980056986e-08, |
|
"loss": 0.0215, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"step": 3510, |
|
"total_flos": 1.7334995773718016e+17, |
|
"train_loss": 0.09133690474209961, |
|
"train_runtime": 2940.2636, |
|
"train_samples_per_second": 229.058, |
|
"train_steps_per_second": 1.194 |
|
} |
|
], |
|
"max_steps": 3510, |
|
"num_train_epochs": 10, |
|
"total_flos": 1.7334995773718016e+17, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|