|
{ |
|
"best_metric": 1.0628538131713867, |
|
"best_model_checkpoint": "bygpt5_quatags_con/medium/en/checkpoint-90832", |
|
"epoch": 7.999955964595535, |
|
"global_step": 90832, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 3.948830567446131e-05, |
|
"loss": 1.2434, |
|
"step": 11354 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 1.1300886869430542, |
|
"eval_runtime": 441.3582, |
|
"eval_samples_per_second": 45.736, |
|
"eval_steps_per_second": 5.719, |
|
"step": 11354 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 3.704453340788571e-05, |
|
"loss": 1.1308, |
|
"step": 22708 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 1.1001691818237305, |
|
"eval_runtime": 440.6446, |
|
"eval_samples_per_second": 45.81, |
|
"eval_steps_per_second": 5.728, |
|
"step": 22708 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 3.282841708036157e-05, |
|
"loss": 1.0962, |
|
"step": 34062 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_loss": 1.082809329032898, |
|
"eval_runtime": 440.424, |
|
"eval_samples_per_second": 45.833, |
|
"eval_steps_per_second": 5.731, |
|
"step": 34062 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"learning_rate": 2.727836169568317e-05, |
|
"loss": 1.0715, |
|
"step": 45416 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_loss": 1.073394536972046, |
|
"eval_runtime": 440.7618, |
|
"eval_samples_per_second": 45.798, |
|
"eval_steps_per_second": 5.726, |
|
"step": 45416 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 2.0971479426039337e-05, |
|
"loss": 1.0522, |
|
"step": 56770 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_loss": 1.0667953491210938, |
|
"eval_runtime": 440.157, |
|
"eval_samples_per_second": 45.861, |
|
"eval_steps_per_second": 5.734, |
|
"step": 56770 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"learning_rate": 1.4563579677660773e-05, |
|
"loss": 1.0372, |
|
"step": 68124 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"eval_loss": 1.0641292333602905, |
|
"eval_runtime": 439.9553, |
|
"eval_samples_per_second": 45.882, |
|
"eval_steps_per_second": 5.737, |
|
"step": 68124 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"learning_rate": 8.720975971159198e-06, |
|
"loss": 1.0258, |
|
"step": 79478 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"eval_loss": 1.0637840032577515, |
|
"eval_runtime": 440.5762, |
|
"eval_samples_per_second": 45.817, |
|
"eval_steps_per_second": 5.729, |
|
"step": 79478 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"learning_rate": 4.051200571096512e-06, |
|
"loss": 1.0178, |
|
"step": 90832 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"eval_loss": 1.0628538131713867, |
|
"eval_runtime": 440.6394, |
|
"eval_samples_per_second": 45.811, |
|
"eval_steps_per_second": 5.728, |
|
"step": 90832 |
|
} |
|
], |
|
"max_steps": 113540, |
|
"num_train_epochs": 10, |
|
"total_flos": 5.170056667435008e+17, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|