|
{ |
|
"best_metric": 0.5534710884094238, |
|
"best_model_checkpoint": "wavlm-tamil-ipa/checkpoint-1000", |
|
"epoch": 0.7136485280999108, |
|
"global_step": 1000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 2.97e-05, |
|
"loss": 6.4757, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 5.94e-05, |
|
"loss": 2.7305, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 8.939999999999999e-05, |
|
"loss": 2.5809, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.0001191, |
|
"loss": 2.53, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 0.00014879999999999998, |
|
"loss": 2.0147, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"eval_cer": 0.6800635831193839, |
|
"eval_loss": 1.4391984939575195, |
|
"eval_runtime": 1401.2346, |
|
"eval_samples_per_second": 8.599, |
|
"eval_steps_per_second": 1.075, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 0.00017849999999999997, |
|
"loss": 0.934, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 0.00020819999999999996, |
|
"loss": 0.597, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 0.0002382, |
|
"loss": 0.4904, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 0.0002676, |
|
"loss": 0.4568, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 0.00029759999999999997, |
|
"loss": 0.3961, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"eval_cer": 0.3502788029525032, |
|
"eval_loss": 0.5534710884094238, |
|
"eval_runtime": 1403.4751, |
|
"eval_samples_per_second": 8.585, |
|
"eval_steps_per_second": 1.074, |
|
"step": 1000 |
|
} |
|
], |
|
"max_steps": 70050, |
|
"num_train_epochs": 50, |
|
"total_flos": 6.366682745104583e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|