|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.214, |
|
"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": 6.712113404111031e-06, |
|
"loss": 0.4718, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 8.360489289678585e-06, |
|
"loss": 0.2526, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 9.28666248215634e-06, |
|
"loss": 0.1991, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 9.933858671331224e-06, |
|
"loss": 0.1734, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 9.766666666666667e-06, |
|
"loss": 0.1598, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 9.48888888888889e-06, |
|
"loss": 0.1492, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 9.211111111111111e-06, |
|
"loss": 0.1379, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 8.933333333333333e-06, |
|
"loss": 0.1316, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 8.655555555555557e-06, |
|
"loss": 0.1255, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 8.38888888888889e-06, |
|
"loss": 0.1139, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 8.111111111111112e-06, |
|
"loss": 0.1126, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 7.844444444444446e-06, |
|
"loss": 0.1126, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 7.566666666666667e-06, |
|
"loss": 0.1129, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 7.28888888888889e-06, |
|
"loss": 0.1047, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 7.011111111111112e-06, |
|
"loss": 0.0969, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 6.733333333333334e-06, |
|
"loss": 0.0981, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 6.455555555555556e-06, |
|
"loss": 0.1018, |
|
"step": 425 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 6.177777777777778e-06, |
|
"loss": 0.0925, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 5.9e-06, |
|
"loss": 0.0876, |
|
"step": 475 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 5.622222222222222e-06, |
|
"loss": 0.089, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 5.344444444444446e-06, |
|
"loss": 0.0859, |
|
"step": 525 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 5.0666666666666676e-06, |
|
"loss": 0.0835, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 4.7888888888888894e-06, |
|
"loss": 0.0831, |
|
"step": 575 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 4.511111111111111e-06, |
|
"loss": 0.0911, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 4.233333333333334e-06, |
|
"loss": 0.0838, |
|
"step": 625 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 3.955555555555556e-06, |
|
"loss": 0.0665, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 3.6777777777777778e-06, |
|
"loss": 0.0638, |
|
"step": 675 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 3.4000000000000005e-06, |
|
"loss": 0.0648, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 3.1222222222222228e-06, |
|
"loss": 0.0602, |
|
"step": 725 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 2.8444444444444446e-06, |
|
"loss": 0.07, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 2.566666666666667e-06, |
|
"loss": 0.0716, |
|
"step": 775 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 2.2888888888888892e-06, |
|
"loss": 0.0738, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 2.011111111111111e-06, |
|
"loss": 0.0672, |
|
"step": 825 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 1.7333333333333336e-06, |
|
"loss": 0.0574, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 1.4555555555555557e-06, |
|
"loss": 0.0518, |
|
"step": 875 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 1.1777777777777778e-06, |
|
"loss": 0.0507, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 9.000000000000001e-07, |
|
"loss": 0.0532, |
|
"step": 925 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 6.222222222222223e-07, |
|
"loss": 0.0488, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 3.444444444444445e-07, |
|
"loss": 0.0461, |
|
"step": 975 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 6.666666666666668e-08, |
|
"loss": 0.046, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"eval_loss": 0.0745849609375, |
|
"eval_runtime": 11732.321, |
|
"eval_samples_per_second": 0.712, |
|
"eval_steps_per_second": 0.045, |
|
"eval_wer": 11.108576189814906, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"step": 1000, |
|
"total_flos": 6.789476357545289e+19, |
|
"train_loss": 0.106069580078125, |
|
"train_runtime": 20500.5095, |
|
"train_samples_per_second": 1.561, |
|
"train_steps_per_second": 0.049 |
|
} |
|
], |
|
"max_steps": 1000, |
|
"num_train_epochs": 9223372036854775807, |
|
"total_flos": 6.789476357545289e+19, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|