|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.1510859301227573, |
|
"global_step": 25, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 2.017781116592232e-05, |
|
"loss": 2.0957, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 4.035562233184464e-05, |
|
"loss": 1.8833, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 6.053343531675637e-05, |
|
"loss": 1.835, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 8.071124466368929e-05, |
|
"loss": 1.7892, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.0001008890540106222, |
|
"loss": 1.8125, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00012106687063351274, |
|
"loss": 1.8234, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.00014124467270448804, |
|
"loss": 1.8613, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.00016142248932737857, |
|
"loss": 1.7927, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.0001816003059502691, |
|
"loss": 1.7335, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.0002017781080212444, |
|
"loss": 1.7266, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.00022195592464413494, |
|
"loss": 1.6341, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.00024213374126702547, |
|
"loss": 1.6133, |
|
"step": 24 |
|
} |
|
], |
|
"max_steps": 165, |
|
"num_train_epochs": 1, |
|
"total_flos": 3.50610259968e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|