|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 6.492706645056726, |
|
"global_step": 2000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 0.00023999999999999998, |
|
"loss": 3.5498, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"eval_loss": 0.7558379173278809, |
|
"eval_runtime": 196.0447, |
|
"eval_samples_per_second": 10.156, |
|
"eval_wer": 0.7275141242937853, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 2.6, |
|
"learning_rate": 0.000297029702970297, |
|
"loss": 0.735, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 2.6, |
|
"eval_loss": 0.4254470467567444, |
|
"eval_runtime": 196.081, |
|
"eval_samples_per_second": 10.154, |
|
"eval_wer": 0.521412429378531, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 3.89, |
|
"learning_rate": 0.00029306930693069307, |
|
"loss": 0.502, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 3.89, |
|
"eval_loss": 0.369031697511673, |
|
"eval_runtime": 193.173, |
|
"eval_samples_per_second": 10.307, |
|
"eval_wer": 0.46146892655367233, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 5.19, |
|
"learning_rate": 0.00028910891089108906, |
|
"loss": 0.4002, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 5.19, |
|
"eval_loss": 0.34798651933670044, |
|
"eval_runtime": 194.1431, |
|
"eval_samples_per_second": 10.255, |
|
"eval_wer": 0.4266666666666667, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 6.49, |
|
"learning_rate": 0.0002851485148514851, |
|
"loss": 0.3301, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 6.49, |
|
"eval_loss": 0.34466618299484253, |
|
"eval_runtime": 194.5915, |
|
"eval_samples_per_second": 10.232, |
|
"eval_wer": 0.41836158192090395, |
|
"step": 2000 |
|
} |
|
], |
|
"max_steps": 30800, |
|
"num_train_epochs": 100, |
|
"total_flos": 6.866081544696079e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|