|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 30.0, |
|
"global_step": 1740, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 8.62, |
|
"learning_rate": 3.563218390804598e-05, |
|
"loss": 2.043, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 17.24, |
|
"learning_rate": 2.1264367816091954e-05, |
|
"loss": 1.539, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 25.86, |
|
"learning_rate": 6.896551724137932e-06, |
|
"loss": 1.2681, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 30.0, |
|
"step": 1740, |
|
"total_flos": 6403012579676160.0, |
|
"train_loss": 1.552490357146866, |
|
"train_runtime": 2803.476, |
|
"train_samples_per_second": 2.451, |
|
"train_steps_per_second": 0.621 |
|
} |
|
], |
|
"max_steps": 1740, |
|
"num_train_epochs": 30, |
|
"total_flos": 6403012579676160.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|