|
{ |
|
"best_metric": 11.942264272658853, |
|
"best_model_checkpoint": "./checkpoint-1000", |
|
"epoch": 3.0208, |
|
"global_step": 1000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 9.200000000000001e-07, |
|
"loss": 0.5204, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 1.9200000000000003e-06, |
|
"loss": 0.0582, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 2.92e-06, |
|
"loss": 0.0527, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 3.920000000000001e-06, |
|
"loss": 0.0587, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 4.92e-06, |
|
"loss": 0.0659, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 5.92e-06, |
|
"loss": 0.0681, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 6.92e-06, |
|
"loss": 0.07, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 7.92e-06, |
|
"loss": 0.0856, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 8.920000000000001e-06, |
|
"loss": 0.0894, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 9.920000000000002e-06, |
|
"loss": 0.0751, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 9.89777777777778e-06, |
|
"loss": 0.0772, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 9.786666666666667e-06, |
|
"loss": 0.0698, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 9.675555555555555e-06, |
|
"loss": 0.0893, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 9.564444444444445e-06, |
|
"loss": 0.0782, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 9.453333333333335e-06, |
|
"loss": 0.0595, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 9.342222222222223e-06, |
|
"loss": 0.0537, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 9.231111111111111e-06, |
|
"loss": 0.052, |
|
"step": 425 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 9.12e-06, |
|
"loss": 0.05, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 9.008888888888889e-06, |
|
"loss": 0.0522, |
|
"step": 475 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 8.897777777777779e-06, |
|
"loss": 0.0467, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 8.786666666666668e-06, |
|
"loss": 0.0586, |
|
"step": 525 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 8.675555555555556e-06, |
|
"loss": 0.0437, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 8.564444444444445e-06, |
|
"loss": 0.0395, |
|
"step": 575 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 8.453333333333334e-06, |
|
"loss": 0.0371, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 8.342222222222222e-06, |
|
"loss": 0.0316, |
|
"step": 625 |
|
}, |
|
{ |
|
"epoch": 2.01, |
|
"learning_rate": 8.231111111111112e-06, |
|
"loss": 0.0412, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 2.02, |
|
"learning_rate": 8.120000000000002e-06, |
|
"loss": 0.0335, |
|
"step": 675 |
|
}, |
|
{ |
|
"epoch": 2.03, |
|
"learning_rate": 8.00888888888889e-06, |
|
"loss": 0.0314, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 2.04, |
|
"learning_rate": 7.897777777777778e-06, |
|
"loss": 0.0329, |
|
"step": 725 |
|
}, |
|
{ |
|
"epoch": 2.05, |
|
"learning_rate": 7.786666666666666e-06, |
|
"loss": 0.0275, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 2.06, |
|
"learning_rate": 7.675555555555556e-06, |
|
"loss": 0.028, |
|
"step": 775 |
|
}, |
|
{ |
|
"epoch": 2.07, |
|
"learning_rate": 7.564444444444446e-06, |
|
"loss": 0.0256, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"learning_rate": 7.453333333333334e-06, |
|
"loss": 0.026, |
|
"step": 825 |
|
}, |
|
{ |
|
"epoch": 2.09, |
|
"learning_rate": 7.342222222222223e-06, |
|
"loss": 0.0295, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 2.1, |
|
"learning_rate": 7.231111111111112e-06, |
|
"loss": 0.0259, |
|
"step": 875 |
|
}, |
|
{ |
|
"epoch": 2.11, |
|
"learning_rate": 7.1200000000000004e-06, |
|
"loss": 0.0173, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 2.12, |
|
"learning_rate": 7.008888888888889e-06, |
|
"loss": 0.014, |
|
"step": 925 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 6.897777777777779e-06, |
|
"loss": 0.0158, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 3.01, |
|
"learning_rate": 6.786666666666667e-06, |
|
"loss": 0.0193, |
|
"step": 975 |
|
}, |
|
{ |
|
"epoch": 3.02, |
|
"learning_rate": 6.675555555555556e-06, |
|
"loss": 0.0146, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 3.02, |
|
"eval_loss": 0.2546452581882477, |
|
"eval_runtime": 2882.0567, |
|
"eval_samples_per_second": 1.759, |
|
"eval_steps_per_second": 0.11, |
|
"eval_wer": 11.942264272658853, |
|
"step": 1000 |
|
} |
|
], |
|
"max_steps": 2500, |
|
"num_train_epochs": 9223372036854775807, |
|
"total_flos": 3.263486252285952e+19, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|