|
{ |
|
"best_metric": 0.07856032524213799, |
|
"best_model_checkpoint": "./wav2vec2-xls-r-300m-ar/checkpoint-1000", |
|
"epoch": 8.849557522123893, |
|
"global_step": 1000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 1.4999999999999999e-05, |
|
"loss": 9.1248, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 2.9999999999999997e-05, |
|
"loss": 6.6739, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 4.4999999999999996e-05, |
|
"loss": 4.632, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 5.9999999999999995e-05, |
|
"loss": 3.917, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 7.5e-05, |
|
"loss": 3.3449, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 8.999999999999999e-05, |
|
"loss": 2.8486, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.55, |
|
"learning_rate": 0.00010499999999999999, |
|
"loss": 2.5717, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 1.77, |
|
"learning_rate": 0.00011999999999999999, |
|
"loss": 2.3746, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.99, |
|
"learning_rate": 0.000135, |
|
"loss": 2.2744, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 2.21, |
|
"learning_rate": 0.00015, |
|
"loss": 2.0759, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 2.43, |
|
"learning_rate": 0.000165, |
|
"loss": 1.7813, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 2.65, |
|
"learning_rate": 0.00017999999999999998, |
|
"loss": 1.2002, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 2.88, |
|
"learning_rate": 0.000195, |
|
"loss": 0.7684, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 3.1, |
|
"learning_rate": 0.00020999999999999998, |
|
"loss": 0.527, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 3.32, |
|
"learning_rate": 0.000225, |
|
"loss": 0.3734, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 3.54, |
|
"learning_rate": 0.00023999999999999998, |
|
"loss": 0.3184, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 3.76, |
|
"learning_rate": 0.00025499999999999996, |
|
"loss": 0.2822, |
|
"step": 425 |
|
}, |
|
{ |
|
"epoch": 3.98, |
|
"learning_rate": 0.00027, |
|
"loss": 0.2074, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 4.2, |
|
"learning_rate": 0.000285, |
|
"loss": 0.1985, |
|
"step": 475 |
|
}, |
|
{ |
|
"epoch": 4.42, |
|
"learning_rate": 0.0003, |
|
"loss": 0.1917, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 4.65, |
|
"learning_rate": 0.00029921052631578946, |
|
"loss": 0.1853, |
|
"step": 525 |
|
}, |
|
{ |
|
"epoch": 4.87, |
|
"learning_rate": 0.00029842105263157894, |
|
"loss": 0.1828, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 5.09, |
|
"learning_rate": 0.00029763157894736837, |
|
"loss": 0.1715, |
|
"step": 575 |
|
}, |
|
{ |
|
"epoch": 5.31, |
|
"learning_rate": 0.00029684210526315785, |
|
"loss": 0.1457, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 5.53, |
|
"learning_rate": 0.00029605263157894733, |
|
"loss": 0.1247, |
|
"step": 625 |
|
}, |
|
{ |
|
"epoch": 5.75, |
|
"learning_rate": 0.0002952631578947368, |
|
"loss": 0.1266, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 5.97, |
|
"learning_rate": 0.0002944736842105263, |
|
"loss": 0.117, |
|
"step": 675 |
|
}, |
|
{ |
|
"epoch": 6.19, |
|
"learning_rate": 0.0002936842105263158, |
|
"loss": 0.117, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 6.42, |
|
"learning_rate": 0.00029289473684210527, |
|
"loss": 0.125, |
|
"step": 725 |
|
}, |
|
{ |
|
"epoch": 6.64, |
|
"learning_rate": 0.0002921052631578947, |
|
"loss": 0.1084, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 6.86, |
|
"learning_rate": 0.0002913157894736842, |
|
"loss": 0.1178, |
|
"step": 775 |
|
}, |
|
{ |
|
"epoch": 7.08, |
|
"learning_rate": 0.00029052631578947366, |
|
"loss": 0.1193, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 7.3, |
|
"learning_rate": 0.00028973684210526314, |
|
"loss": 0.0925, |
|
"step": 825 |
|
}, |
|
{ |
|
"epoch": 7.52, |
|
"learning_rate": 0.00028894736842105263, |
|
"loss": 0.085, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 7.74, |
|
"learning_rate": 0.00028815789473684206, |
|
"loss": 0.0865, |
|
"step": 875 |
|
}, |
|
{ |
|
"epoch": 7.96, |
|
"learning_rate": 0.00028736842105263154, |
|
"loss": 0.0811, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 8.19, |
|
"learning_rate": 0.000286578947368421, |
|
"loss": 0.0835, |
|
"step": 925 |
|
}, |
|
{ |
|
"epoch": 8.41, |
|
"learning_rate": 0.0002857894736842105, |
|
"loss": 0.0886, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 8.63, |
|
"learning_rate": 0.000285, |
|
"loss": 0.0991, |
|
"step": 975 |
|
}, |
|
{ |
|
"epoch": 8.85, |
|
"learning_rate": 0.0002842105263157894, |
|
"loss": 0.0793, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 8.85, |
|
"eval_loss": 0.16262491047382355, |
|
"eval_runtime": 11.6481, |
|
"eval_samples_per_second": 8.585, |
|
"eval_steps_per_second": 1.116, |
|
"eval_wer": 0.07856032524213799, |
|
"step": 1000 |
|
} |
|
], |
|
"max_steps": 10000, |
|
"num_train_epochs": 89, |
|
"total_flos": 3.9707238818974925e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|