|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.0, |
|
"global_step": 2547, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 4.018453082057323e-05, |
|
"loss": 4.6162, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 3.0369061641146445e-05, |
|
"loss": 3.5948, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 1.77, |
|
"learning_rate": 2.055359246171967e-05, |
|
"loss": 3.1184, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 2.36, |
|
"learning_rate": 1.0738123282292894e-05, |
|
"loss": 2.7712, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 2.94, |
|
"learning_rate": 9.22654102866117e-07, |
|
"loss": 2.5399, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 2547, |
|
"total_flos": 677154582454272.0, |
|
"train_loss": 3.3112940224751237, |
|
"train_runtime": 405.5773, |
|
"train_samples_per_second": 25.112, |
|
"train_steps_per_second": 6.28 |
|
} |
|
], |
|
"max_steps": 2547, |
|
"num_train_epochs": 3, |
|
"total_flos": 677154582454272.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|