|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.9786407766990292, |
|
"global_step": 42, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 2.631578947368421e-06, |
|
"loss": 1.6384, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 5.263157894736842e-06, |
|
"loss": 1.677, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 7.894736842105263e-06, |
|
"loss": 1.9569, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 1.0526315789473684e-05, |
|
"loss": 1.8787, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 1.3157894736842106e-05, |
|
"loss": 1.9318, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 1.5789473684210526e-05, |
|
"loss": 2.1207, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 1.8421052631578947e-05, |
|
"loss": 2.0227, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 2.105263157894737e-05, |
|
"loss": 2.103, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 2.368421052631579e-05, |
|
"loss": 2.2184, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 2.6315789473684212e-05, |
|
"loss": 2.455, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 2.8947368421052634e-05, |
|
"loss": 1.6635, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 3.157894736842105e-05, |
|
"loss": 1.6389, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 3.421052631578947e-05, |
|
"loss": 1.7803, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 3.6842105263157895e-05, |
|
"loss": 1.8378, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 3.9473684210526316e-05, |
|
"loss": 1.9676, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 4.210526315789474e-05, |
|
"loss": 2.0158, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 4.473684210526316e-05, |
|
"loss": 1.8251, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 4.736842105263158e-05, |
|
"loss": 1.9671, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 5e-05, |
|
"loss": 1.9491, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 5.2631578947368424e-05, |
|
"loss": 1.9589, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 5.526315789473685e-05, |
|
"loss": 1.6453, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 5.789473684210527e-05, |
|
"loss": 1.5859, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 6.052631578947369e-05, |
|
"loss": 1.7574, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 6.31578947368421e-05, |
|
"loss": 1.8601, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 6.578947368421054e-05, |
|
"loss": 1.7867, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 6.842105263157895e-05, |
|
"loss": 1.9736, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 7.105263157894737e-05, |
|
"loss": 1.96, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 7.368421052631579e-05, |
|
"loss": 1.7974, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 7.631578947368422e-05, |
|
"loss": 1.8705, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 7.894736842105263e-05, |
|
"loss": 1.8634, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 8.157894736842105e-05, |
|
"loss": 1.6359, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 8.421052631578948e-05, |
|
"loss": 1.6283, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 8.68421052631579e-05, |
|
"loss": 1.8596, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 8.947368421052632e-05, |
|
"loss": 1.7455, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 9.210526315789474e-05, |
|
"loss": 1.7927, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 9.473684210526316e-05, |
|
"loss": 1.8419, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 9.736842105263158e-05, |
|
"loss": 1.8011, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 0.0001, |
|
"loss": 1.8074, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 9.983108108108109e-05, |
|
"loss": 2.0587, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 9.966216216216217e-05, |
|
"loss": 1.9083, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 9.949324324324325e-05, |
|
"loss": 1.7381, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 9.932432432432433e-05, |
|
"loss": 1.9415, |
|
"step": 42 |
|
} |
|
], |
|
"max_steps": 630, |
|
"num_train_epochs": 15, |
|
"total_flos": 1.553589993897984e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|