|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.0, |
|
"global_step": 2103, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 3.811222063718498e-05, |
|
"loss": 2.9453, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 2.6224441274369948e-05, |
|
"loss": 2.2715, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 2.14, |
|
"learning_rate": 1.433666191155492e-05, |
|
"loss": 1.9929, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 2.85, |
|
"learning_rate": 2.4488825487398953e-06, |
|
"loss": 1.6983, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 2103, |
|
"total_flos": 599644615606272.0, |
|
"train_loss": 2.2007998014369354, |
|
"train_runtime": 350.3477, |
|
"train_samples_per_second": 23.993, |
|
"train_steps_per_second": 6.003 |
|
} |
|
], |
|
"max_steps": 2103, |
|
"num_train_epochs": 3, |
|
"total_flos": 599644615606272.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|