|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.5, |
|
"eval_steps": 20, |
|
"global_step": 150, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 1e-05, |
|
"loss": 0.588, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 2e-05, |
|
"loss": 0.5793, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"eval_loss": 0.5849277377128601, |
|
"eval_runtime": 13.5251, |
|
"eval_samples_per_second": 1.848, |
|
"eval_steps_per_second": 0.296, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 3e-05, |
|
"loss": 0.5065, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 4e-05, |
|
"loss": 0.5404, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"eval_loss": 0.5613898634910583, |
|
"eval_runtime": 13.3646, |
|
"eval_samples_per_second": 1.871, |
|
"eval_steps_per_second": 0.299, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 5e-05, |
|
"loss": 0.4523, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 4.9986331433523156e-05, |
|
"loss": 0.5692, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"eval_loss": 0.5513718724250793, |
|
"eval_runtime": 13.3937, |
|
"eval_samples_per_second": 1.867, |
|
"eval_steps_per_second": 0.299, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 4.994534068046937e-05, |
|
"loss": 0.5257, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 4.9877072563625285e-05, |
|
"loss": 0.4937, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"eval_loss": 0.5424299836158752, |
|
"eval_runtime": 13.4443, |
|
"eval_samples_per_second": 1.86, |
|
"eval_steps_per_second": 0.298, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 4.978160173317438e-05, |
|
"loss": 0.5617, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 4.965903258506806e-05, |
|
"loss": 0.3592, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 0.5260083675384521, |
|
"eval_runtime": 13.4207, |
|
"eval_samples_per_second": 1.863, |
|
"eval_steps_per_second": 0.298, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 4.9509499146870236e-05, |
|
"loss": 0.4586, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 4.933316493120015e-05, |
|
"loss": 0.3724, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"eval_loss": 0.5247484445571899, |
|
"eval_runtime": 13.4092, |
|
"eval_samples_per_second": 1.864, |
|
"eval_steps_per_second": 0.298, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 4.913022275693372e-05, |
|
"loss": 0.3205, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 4.8900894538358944e-05, |
|
"loss": 0.4962, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"eval_loss": 0.5248944163322449, |
|
"eval_runtime": 13.4511, |
|
"eval_samples_per_second": 1.859, |
|
"eval_steps_per_second": 0.297, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 4.864543104251587e-05, |
|
"loss": 0.3324, |
|
"step": 150 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 1000, |
|
"num_train_epochs": 10, |
|
"save_steps": 50, |
|
"total_flos": 2.1126003395395584e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|