|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.0, |
|
"global_step": 1650, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 2.090909090909091e-05, |
|
"loss": 1.2525, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 1.1818181818181819e-05, |
|
"loss": 1.0478, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 1.82, |
|
"learning_rate": 2.7272727272727272e-06, |
|
"loss": 0.5, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"step": 1650, |
|
"total_flos": 8622543790080000.0, |
|
"train_loss": 0.9066677579012784, |
|
"train_runtime": 893.6642, |
|
"train_samples_per_second": 3.693, |
|
"train_steps_per_second": 1.846 |
|
} |
|
], |
|
"max_steps": 1650, |
|
"num_train_epochs": 2, |
|
"total_flos": 8622543790080000.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|