|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 57.142857142857146, |
|
"global_step": 400, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 7.14, |
|
"learning_rate": 8.850000000000001e-05, |
|
"loss": 1.8163, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 14.29, |
|
"learning_rate": 7.6e-05, |
|
"loss": 0.0145, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 21.43, |
|
"learning_rate": 6.35e-05, |
|
"loss": 0.0015, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 28.57, |
|
"learning_rate": 5.1000000000000006e-05, |
|
"loss": 0.0007, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 35.71, |
|
"learning_rate": 3.85e-05, |
|
"loss": 0.0006, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 42.86, |
|
"learning_rate": 2.6000000000000002e-05, |
|
"loss": 0.0005, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 50.0, |
|
"learning_rate": 1.3500000000000001e-05, |
|
"loss": 0.0004, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 57.14, |
|
"learning_rate": 1.0000000000000002e-06, |
|
"loss": 0.0004, |
|
"step": 400 |
|
} |
|
], |
|
"max_steps": 400, |
|
"num_train_epochs": 58, |
|
"total_flos": 5098502646595584.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|