|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 100.0, |
|
"global_step": 2900, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 17.24, |
|
"learning_rate": 0.00041379310344827585, |
|
"loss": 2.4, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 34.48, |
|
"learning_rate": 0.0003275862068965517, |
|
"loss": 1.5498, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 51.72, |
|
"learning_rate": 0.0002413793103448276, |
|
"loss": 1.0188, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 68.97, |
|
"learning_rate": 0.00015517241379310346, |
|
"loss": 0.6721, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 86.21, |
|
"learning_rate": 6.896551724137931e-05, |
|
"loss": 0.4353, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 100.0, |
|
"step": 2900, |
|
"total_flos": 6027390213120000.0, |
|
"train_loss": 1.0904766319537984, |
|
"train_runtime": 2826.0502, |
|
"train_samples_per_second": 8.103, |
|
"train_steps_per_second": 1.026 |
|
} |
|
], |
|
"max_steps": 2900, |
|
"num_train_epochs": 100, |
|
"total_flos": 6027390213120000.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|