|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.0, |
|
"global_step": 1236, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 2.9773462783171523e-05, |
|
"loss": 3.1968, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 2.43, |
|
"learning_rate": 9.546925566343042e-06, |
|
"loss": 1.8077, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 1236, |
|
"total_flos": 380716259278848.0, |
|
"train_loss": 2.290668154225766, |
|
"train_runtime": 2303.4288, |
|
"train_samples_per_second": 2.142, |
|
"train_steps_per_second": 0.537 |
|
} |
|
], |
|
"max_steps": 1236, |
|
"num_train_epochs": 3, |
|
"total_flos": 380716259278848.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|