|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 71.006, |
|
"global_step": 1000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 7.90139129823451e-06, |
|
"loss": 0.3987, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 3.01, |
|
"learning_rate": 9.841832720226257e-06, |
|
"loss": 0.0999, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 9.778947368421054e-06, |
|
"loss": 0.0373, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"learning_rate": 9.515789473684212e-06, |
|
"loss": 0.0217, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 8.01, |
|
"learning_rate": 9.252631578947368e-06, |
|
"loss": 0.0143, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 10.01, |
|
"learning_rate": 9e-06, |
|
"loss": 0.0095, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 12.01, |
|
"learning_rate": 8.736842105263158e-06, |
|
"loss": 0.0092, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 14.0, |
|
"learning_rate": 8.473684210526317e-06, |
|
"loss": 0.0065, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 16.0, |
|
"learning_rate": 8.210526315789475e-06, |
|
"loss": 0.0026, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 17.01, |
|
"learning_rate": 7.947368421052633e-06, |
|
"loss": 0.0021, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 19.01, |
|
"learning_rate": 7.68421052631579e-06, |
|
"loss": 0.0019, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 21.01, |
|
"learning_rate": 7.421052631578948e-06, |
|
"loss": 0.0016, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 23.0, |
|
"learning_rate": 7.157894736842106e-06, |
|
"loss": 0.0013, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 24.01, |
|
"learning_rate": 6.894736842105264e-06, |
|
"loss": 0.0021, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 26.01, |
|
"learning_rate": 6.631578947368421e-06, |
|
"loss": 0.001, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 28.01, |
|
"learning_rate": 6.3684210526315795e-06, |
|
"loss": 0.0011, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 30.0, |
|
"learning_rate": 6.105263157894738e-06, |
|
"loss": 0.0002, |
|
"step": 425 |
|
}, |
|
{ |
|
"epoch": 32.0, |
|
"learning_rate": 5.842105263157896e-06, |
|
"loss": 0.0001, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 33.01, |
|
"learning_rate": 5.578947368421052e-06, |
|
"loss": 0.0001, |
|
"step": 475 |
|
}, |
|
{ |
|
"epoch": 35.01, |
|
"learning_rate": 5.315789473684211e-06, |
|
"loss": 0.0, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 37.01, |
|
"learning_rate": 5.052631578947369e-06, |
|
"loss": 0.0, |
|
"step": 525 |
|
}, |
|
{ |
|
"epoch": 39.0, |
|
"learning_rate": 4.789473684210527e-06, |
|
"loss": 0.0, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 41.0, |
|
"learning_rate": 4.526315789473685e-06, |
|
"loss": 0.0, |
|
"step": 575 |
|
}, |
|
{ |
|
"epoch": 42.01, |
|
"learning_rate": 4.2631578947368425e-06, |
|
"loss": 0.0, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 44.01, |
|
"learning_rate": 4.000000000000001e-06, |
|
"loss": 0.0, |
|
"step": 625 |
|
}, |
|
{ |
|
"epoch": 46.01, |
|
"learning_rate": 3.736842105263158e-06, |
|
"loss": 0.0, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 48.0, |
|
"learning_rate": 3.473684210526316e-06, |
|
"loss": 0.0, |
|
"step": 675 |
|
}, |
|
{ |
|
"epoch": 49.01, |
|
"learning_rate": 3.210526315789474e-06, |
|
"loss": 0.0, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 51.01, |
|
"learning_rate": 2.9473684210526317e-06, |
|
"loss": 0.0, |
|
"step": 725 |
|
}, |
|
{ |
|
"epoch": 53.01, |
|
"learning_rate": 2.68421052631579e-06, |
|
"loss": 0.0, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 55.01, |
|
"learning_rate": 2.4210526315789477e-06, |
|
"loss": 0.0, |
|
"step": 775 |
|
}, |
|
{ |
|
"epoch": 57.0, |
|
"learning_rate": 2.1578947368421054e-06, |
|
"loss": 0.0, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 58.01, |
|
"learning_rate": 1.8947368421052634e-06, |
|
"loss": 0.0, |
|
"step": 825 |
|
}, |
|
{ |
|
"epoch": 60.01, |
|
"learning_rate": 1.6315789473684212e-06, |
|
"loss": 0.0, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 62.01, |
|
"learning_rate": 1.3684210526315791e-06, |
|
"loss": 0.0, |
|
"step": 875 |
|
}, |
|
{ |
|
"epoch": 64.0, |
|
"learning_rate": 1.1052631578947369e-06, |
|
"loss": 0.0, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 66.0, |
|
"learning_rate": 8.421052631578948e-07, |
|
"loss": 0.0, |
|
"step": 925 |
|
}, |
|
{ |
|
"epoch": 67.01, |
|
"learning_rate": 5.789473684210526e-07, |
|
"loss": 0.0, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 69.01, |
|
"learning_rate": 3.1578947368421055e-07, |
|
"loss": 0.0, |
|
"step": 975 |
|
}, |
|
{ |
|
"epoch": 71.01, |
|
"learning_rate": 5.263157894736842e-08, |
|
"loss": 0.0, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 71.01, |
|
"eval_loss": 0.4169921875, |
|
"eval_runtime": 145.8577, |
|
"eval_samples_per_second": 0.768, |
|
"eval_steps_per_second": 0.048, |
|
"eval_wer": 25.478927203065133, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 71.01, |
|
"step": 1000, |
|
"total_flos": 6.5228059200735674e+19, |
|
"train_loss": 0.015296513795852661, |
|
"train_runtime": 8456.11, |
|
"train_samples_per_second": 3.784, |
|
"train_steps_per_second": 0.118 |
|
} |
|
], |
|
"max_steps": 1000, |
|
"num_train_epochs": 9223372036854775807, |
|
"total_flos": 6.5228059200735674e+19, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|