|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 10.0, |
|
"global_step": 3970, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 4.370277078085643e-05, |
|
"loss": 2.513, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 2.52, |
|
"learning_rate": 3.7405541561712845e-05, |
|
"loss": 1.1385, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 3.78, |
|
"learning_rate": 3.1108312342569276e-05, |
|
"loss": 1.0013, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 5.04, |
|
"learning_rate": 2.4811083123425694e-05, |
|
"loss": 0.941, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 6.3, |
|
"learning_rate": 1.8513853904282116e-05, |
|
"loss": 0.8986, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 7.56, |
|
"learning_rate": 1.2216624685138539e-05, |
|
"loss": 0.8733, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 8.82, |
|
"learning_rate": 5.919395465994963e-06, |
|
"loss": 0.8501, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"step": 3970, |
|
"total_flos": 2209316430643200.0, |
|
"train_loss": 1.1338991256444821, |
|
"train_runtime": 517.5257, |
|
"train_samples_per_second": 122.448, |
|
"train_steps_per_second": 7.671 |
|
} |
|
], |
|
"max_steps": 3970, |
|
"num_train_epochs": 10, |
|
"total_flos": 2209316430643200.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|