|
{ |
|
"best_metric": 644.20410427066, |
|
"best_model_checkpoint": "./whisper-tiny-it-7/checkpoint-1000", |
|
"epoch": 0.9541984732824428, |
|
"global_step": 1000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 4e-08, |
|
"loss": 8.8525, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 9e-08, |
|
"loss": 8.857, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 1.4e-07, |
|
"loss": 8.6107, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 1.8999999999999998e-07, |
|
"loss": 8.1659, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 2.4e-07, |
|
"loss": 7.7359, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 2.9e-07, |
|
"loss": 7.2816, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 3.4000000000000003e-07, |
|
"loss": 6.9829, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 3.8999999999999997e-07, |
|
"loss": 6.5257, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 4.3999999999999997e-07, |
|
"loss": 6.1594, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 4.9e-07, |
|
"loss": 5.9187, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 5.4e-07, |
|
"loss": 5.7123, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 5.9e-07, |
|
"loss": 5.4899, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 6.4e-07, |
|
"loss": 5.1635, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 6.9e-07, |
|
"loss": 4.9477, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 7.4e-07, |
|
"loss": 4.8882, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 7.9e-07, |
|
"loss": 4.7571, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 8.399999999999999e-07, |
|
"loss": 4.7402, |
|
"step": 425 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 8.9e-07, |
|
"loss": 4.6719, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 9.399999999999999e-07, |
|
"loss": 4.5627, |
|
"step": 475 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 9.9e-07, |
|
"loss": 4.6078, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 9.942857142857144e-07, |
|
"loss": 4.5315, |
|
"step": 525 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 9.871428571428572e-07, |
|
"loss": 4.4441, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 9.8e-07, |
|
"loss": 4.4877, |
|
"step": 575 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 9.72857142857143e-07, |
|
"loss": 4.4972, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 9.657142857142857e-07, |
|
"loss": 4.4206, |
|
"step": 625 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 9.585714285714285e-07, |
|
"loss": 4.4121, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 9.514285714285713e-07, |
|
"loss": 4.3059, |
|
"step": 675 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 9.442857142857142e-07, |
|
"loss": 4.3611, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 9.371428571428571e-07, |
|
"loss": 4.343, |
|
"step": 725 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 9.3e-07, |
|
"loss": 4.3366, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 9.228571428571428e-07, |
|
"loss": 4.3313, |
|
"step": 775 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 9.157142857142856e-07, |
|
"loss": 4.317, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 9.085714285714285e-07, |
|
"loss": 4.2746, |
|
"step": 825 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 9.014285714285714e-07, |
|
"loss": 4.2817, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 8.942857142857142e-07, |
|
"loss": 4.2529, |
|
"step": 875 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 8.871428571428571e-07, |
|
"loss": 4.248, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 8.799999999999999e-07, |
|
"loss": 4.2731, |
|
"step": 925 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 8.728571428571428e-07, |
|
"loss": 4.2709, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 8.657142857142857e-07, |
|
"loss": 4.2254, |
|
"step": 975 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 8.585714285714285e-07, |
|
"loss": 4.204, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"eval_loss": 4.17011833190918, |
|
"eval_runtime": 1604.0964, |
|
"eval_samples_per_second": 0.935, |
|
"eval_steps_per_second": 0.117, |
|
"eval_wer": 644.20410427066, |
|
"step": 1000 |
|
} |
|
], |
|
"max_steps": 4000, |
|
"num_train_epochs": 4, |
|
"total_flos": 3.9390216192e+17, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|