|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0, |
|
"global_step": 8, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.0002, |
|
"loss": 1.4809, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.0001900968867902419, |
|
"loss": 1.4582, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 0.00016234898018587337, |
|
"loss": 1.2343, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 0.00012225209339563145, |
|
"loss": 1.1173, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 7.774790660436858e-05, |
|
"loss": 1.0159, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 3.7651019814126654e-05, |
|
"loss": 0.9748, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 9.903113209758096e-06, |
|
"loss": 0.9348, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 0.0, |
|
"loss": 0.9422, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"step": 8, |
|
"total_flos": 9228393381888.0, |
|
"train_loss": 1.1448063105344772, |
|
"train_runtime": 181.8282, |
|
"train_samples_per_second": 5.5, |
|
"train_steps_per_second": 0.044 |
|
} |
|
], |
|
"max_steps": 8, |
|
"num_train_epochs": 1, |
|
"total_flos": 9228393381888.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|