|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.0, |
|
"global_step": 1791, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 3.6041317699609156e-05, |
|
"loss": 2.6759, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 2.2082635399218317e-05, |
|
"loss": 1.9214, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 2.51, |
|
"learning_rate": 8.123953098827471e-06, |
|
"loss": 1.5946, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 1791, |
|
"total_flos": 511419755593728.0, |
|
"train_loss": 1.9637743227312778, |
|
"train_runtime": 329.5927, |
|
"train_samples_per_second": 21.709, |
|
"train_steps_per_second": 5.434 |
|
} |
|
], |
|
"max_steps": 1791, |
|
"num_train_epochs": 3, |
|
"total_flos": 511419755593728.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|