|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 6.106, |
|
"global_step": 1000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 6.611096473669596e-06, |
|
"loss": 2.9891, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 8.31378915840787e-06, |
|
"loss": 1.3714, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 9.256291743595376e-06, |
|
"loss": 0.968, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 9.911356165197841e-06, |
|
"loss": 0.896, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 9.777777777777779e-06, |
|
"loss": 0.6865, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 9.5e-06, |
|
"loss": 0.5327, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 9.222222222222224e-06, |
|
"loss": 0.594, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 8.944444444444446e-06, |
|
"loss": 0.4992, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 8.666666666666668e-06, |
|
"loss": 0.406, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 8.38888888888889e-06, |
|
"loss": 0.3695, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 8.111111111111112e-06, |
|
"loss": 0.2951, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 7.833333333333333e-06, |
|
"loss": 0.2381, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 2.03, |
|
"learning_rate": 7.555555555555556e-06, |
|
"loss": 0.2621, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 2.05, |
|
"learning_rate": 7.277777777777778e-06, |
|
"loss": 0.2363, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"learning_rate": 7e-06, |
|
"loss": 0.1719, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 2.1, |
|
"learning_rate": 6.7222222222222235e-06, |
|
"loss": 0.1683, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"learning_rate": 6.444444444444445e-06, |
|
"loss": 0.1332, |
|
"step": 425 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 6.166666666666667e-06, |
|
"loss": 0.121, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 3.03, |
|
"learning_rate": 5.88888888888889e-06, |
|
"loss": 0.1249, |
|
"step": 475 |
|
}, |
|
{ |
|
"epoch": 3.05, |
|
"learning_rate": 5.611111111111112e-06, |
|
"loss": 0.0934, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 3.08, |
|
"learning_rate": 5.333333333333334e-06, |
|
"loss": 0.0872, |
|
"step": 525 |
|
}, |
|
{ |
|
"epoch": 3.1, |
|
"learning_rate": 5.0555555555555555e-06, |
|
"loss": 0.0731, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 3.13, |
|
"learning_rate": 4.777777777777778e-06, |
|
"loss": 0.0667, |
|
"step": 575 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"learning_rate": 4.5e-06, |
|
"loss": 0.0535, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 4.03, |
|
"learning_rate": 4.222222222222223e-06, |
|
"loss": 0.0407, |
|
"step": 625 |
|
}, |
|
{ |
|
"epoch": 4.05, |
|
"learning_rate": 3.944444444444445e-06, |
|
"loss": 0.03, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 4.08, |
|
"learning_rate": 3.6666666666666666e-06, |
|
"loss": 0.0332, |
|
"step": 675 |
|
}, |
|
{ |
|
"epoch": 4.1, |
|
"learning_rate": 3.3888888888888893e-06, |
|
"loss": 0.0512, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 4.13, |
|
"learning_rate": 3.1111111111111116e-06, |
|
"loss": 0.0456, |
|
"step": 725 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 2.8333333333333335e-06, |
|
"loss": 0.0366, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 5.03, |
|
"learning_rate": 2.5555555555555557e-06, |
|
"loss": 0.0185, |
|
"step": 775 |
|
}, |
|
{ |
|
"epoch": 5.05, |
|
"learning_rate": 2.277777777777778e-06, |
|
"loss": 0.0162, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 5.08, |
|
"learning_rate": 2.0000000000000003e-06, |
|
"loss": 0.0155, |
|
"step": 825 |
|
}, |
|
{ |
|
"epoch": 5.11, |
|
"learning_rate": 1.7222222222222224e-06, |
|
"loss": 0.0189, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 5.13, |
|
"learning_rate": 1.4444444444444445e-06, |
|
"loss": 0.0154, |
|
"step": 875 |
|
}, |
|
{ |
|
"epoch": 6.01, |
|
"learning_rate": 1.1666666666666668e-06, |
|
"loss": 0.0164, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 6.03, |
|
"learning_rate": 8.88888888888889e-07, |
|
"loss": 0.0079, |
|
"step": 925 |
|
}, |
|
{ |
|
"epoch": 6.06, |
|
"learning_rate": 6.111111111111112e-07, |
|
"loss": 0.0072, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 6.08, |
|
"learning_rate": 3.3333333333333335e-07, |
|
"loss": 0.0074, |
|
"step": 975 |
|
}, |
|
{ |
|
"epoch": 6.11, |
|
"learning_rate": 5.555555555555556e-08, |
|
"loss": 0.0064, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 6.11, |
|
"eval_loss": 0.77001953125, |
|
"eval_runtime": 585.5484, |
|
"eval_samples_per_second": 3.619, |
|
"eval_steps_per_second": 0.227, |
|
"eval_wer": 37.89510246613407, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 6.11, |
|
"step": 1000, |
|
"total_flos": 6.792873436158257e+19, |
|
"train_loss": 0.2951105651855469, |
|
"train_runtime": 8297.0493, |
|
"train_samples_per_second": 3.857, |
|
"train_steps_per_second": 0.121 |
|
} |
|
], |
|
"max_steps": 1000, |
|
"num_train_epochs": 9223372036854775807, |
|
"total_flos": 6.792873436158257e+19, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|