|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.0, |
|
"global_step": 5546, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 4.774612333213127e-05, |
|
"loss": 1.7894, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 4.549224666426253e-05, |
|
"loss": 1.2681, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 4.32383699963938e-05, |
|
"loss": 1.1511, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 4.0984493328525064e-05, |
|
"loss": 1.1003, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 3.873061666065633e-05, |
|
"loss": 1.0589, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_exact_match": 79.72563859981078, |
|
"eval_f1": 87.33897800522966, |
|
"step": 2773 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 3.6476739992787594e-05, |
|
"loss": 0.8936, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 3.422286332491886e-05, |
|
"loss": 0.7398, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 3.1968986657050125e-05, |
|
"loss": 0.738, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 1.62, |
|
"learning_rate": 2.9715109989181394e-05, |
|
"loss": 0.7341, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"learning_rate": 2.7461233321312656e-05, |
|
"loss": 0.7264, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 1.98, |
|
"learning_rate": 2.5207356653443925e-05, |
|
"loss": 0.728, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_exact_match": 81.2961210974456, |
|
"eval_f1": 88.57827007260809, |
|
"step": 5546 |
|
} |
|
], |
|
"max_steps": 11092, |
|
"num_train_epochs": 4, |
|
"total_flos": 3.4779642825015296e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|