|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 9.001, |
|
"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": 6.505149978319905e-06, |
|
"loss": 1.4407, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 8.266062568876717e-06, |
|
"loss": 0.7384, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 9.225490200071284e-06, |
|
"loss": 0.5419, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 9.888618026444238e-06, |
|
"loss": 0.4384, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 9.78888888888889e-06, |
|
"loss": 0.3515, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 9.511111111111112e-06, |
|
"loss": 0.2833, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 9.233333333333334e-06, |
|
"loss": 0.2293, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 8.955555555555555e-06, |
|
"loss": 0.188, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 8.677777777777779e-06, |
|
"loss": 0.1587, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 2.03, |
|
"learning_rate": 8.400000000000001e-06, |
|
"loss": 0.1237, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 2.05, |
|
"learning_rate": 8.122222222222223e-06, |
|
"loss": 0.1073, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"learning_rate": 7.844444444444446e-06, |
|
"loss": 0.0877, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 2.1, |
|
"learning_rate": 7.566666666666667e-06, |
|
"loss": 0.0767, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 3.02, |
|
"learning_rate": 7.28888888888889e-06, |
|
"loss": 0.0653, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 3.04, |
|
"learning_rate": 7.011111111111112e-06, |
|
"loss": 0.0546, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 3.07, |
|
"learning_rate": 6.733333333333334e-06, |
|
"loss": 0.0479, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 3.09, |
|
"learning_rate": 6.455555555555556e-06, |
|
"loss": 0.0397, |
|
"step": 425 |
|
}, |
|
{ |
|
"epoch": 4.01, |
|
"learning_rate": 6.177777777777778e-06, |
|
"loss": 0.0371, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 4.03, |
|
"learning_rate": 5.9e-06, |
|
"loss": 0.0228, |
|
"step": 475 |
|
}, |
|
{ |
|
"epoch": 4.06, |
|
"learning_rate": 5.622222222222222e-06, |
|
"loss": 0.0228, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 4.08, |
|
"learning_rate": 5.344444444444446e-06, |
|
"loss": 0.0285, |
|
"step": 525 |
|
}, |
|
{ |
|
"epoch": 4.11, |
|
"learning_rate": 5.077777777777778e-06, |
|
"loss": 0.0257, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 5.02, |
|
"learning_rate": 4.800000000000001e-06, |
|
"loss": 0.0166, |
|
"step": 575 |
|
}, |
|
{ |
|
"epoch": 5.04, |
|
"learning_rate": 4.5222222222222225e-06, |
|
"loss": 0.011, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 5.07, |
|
"learning_rate": 4.244444444444445e-06, |
|
"loss": 0.0153, |
|
"step": 625 |
|
}, |
|
{ |
|
"epoch": 5.09, |
|
"learning_rate": 3.966666666666667e-06, |
|
"loss": 0.014, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 6.01, |
|
"learning_rate": 3.688888888888889e-06, |
|
"loss": 0.01, |
|
"step": 675 |
|
}, |
|
{ |
|
"epoch": 6.03, |
|
"learning_rate": 3.4111111111111113e-06, |
|
"loss": 0.0071, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 6.06, |
|
"learning_rate": 3.133333333333334e-06, |
|
"loss": 0.0064, |
|
"step": 725 |
|
}, |
|
{ |
|
"epoch": 6.08, |
|
"learning_rate": 2.855555555555556e-06, |
|
"loss": 0.0058, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 6.11, |
|
"learning_rate": 2.577777777777778e-06, |
|
"loss": 0.0059, |
|
"step": 775 |
|
}, |
|
{ |
|
"epoch": 7.02, |
|
"learning_rate": 2.3000000000000004e-06, |
|
"loss": 0.0037, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 7.05, |
|
"learning_rate": 2.0222222222222223e-06, |
|
"loss": 0.003, |
|
"step": 825 |
|
}, |
|
{ |
|
"epoch": 7.07, |
|
"learning_rate": 1.7444444444444448e-06, |
|
"loss": 0.0034, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 7.1, |
|
"learning_rate": 1.4666666666666669e-06, |
|
"loss": 0.0032, |
|
"step": 875 |
|
}, |
|
{ |
|
"epoch": 8.01, |
|
"learning_rate": 1.188888888888889e-06, |
|
"loss": 0.0029, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 8.04, |
|
"learning_rate": 9.111111111111113e-07, |
|
"loss": 0.0026, |
|
"step": 925 |
|
}, |
|
{ |
|
"epoch": 8.06, |
|
"learning_rate": 6.333333333333334e-07, |
|
"loss": 0.0026, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 8.09, |
|
"learning_rate": 3.555555555555556e-07, |
|
"loss": 0.0025, |
|
"step": 975 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"learning_rate": 7.777777777777778e-08, |
|
"loss": 0.0023, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"eval_loss": 0.361572265625, |
|
"eval_runtime": 564.3144, |
|
"eval_samples_per_second": 2.906, |
|
"eval_steps_per_second": 0.183, |
|
"eval_wer": 18.464443960194668, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"step": 1000, |
|
"total_flos": 6.767395305329315e+19, |
|
"train_loss": 0.13070509910583497, |
|
"train_runtime": 8375.5647, |
|
"train_samples_per_second": 3.821, |
|
"train_steps_per_second": 0.119 |
|
} |
|
], |
|
"max_steps": 1000, |
|
"num_train_epochs": 9223372036854775807, |
|
"total_flos": 6.767395305329315e+19, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|