|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.062, |
|
"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": 4.4e-06, |
|
"loss": 4.7543, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 9.4e-06, |
|
"loss": 2.5163, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 1e-05, |
|
"loss": 1.735, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 1e-05, |
|
"loss": 1.4006, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 1e-05, |
|
"loss": 1.2885, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 1e-05, |
|
"loss": 1.1785, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 1e-05, |
|
"loss": 1.0817, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 1e-05, |
|
"loss": 0.8799, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 1e-05, |
|
"loss": 0.8984, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 1e-05, |
|
"loss": 0.9094, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 1e-05, |
|
"loss": 0.89, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 1e-05, |
|
"loss": 0.8031, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 1e-05, |
|
"loss": 0.7335, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 1e-05, |
|
"loss": 0.6849, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 1e-05, |
|
"loss": 0.7076, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 1e-05, |
|
"loss": 0.7274, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 1e-05, |
|
"loss": 0.6721, |
|
"step": 425 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 1e-05, |
|
"loss": 0.6573, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 1e-05, |
|
"loss": 0.6638, |
|
"step": 475 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 1e-05, |
|
"loss": 0.6045, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 1e-05, |
|
"loss": 0.6303, |
|
"step": 525 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 1e-05, |
|
"loss": 0.555, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 1e-05, |
|
"loss": 0.6402, |
|
"step": 575 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 1e-05, |
|
"loss": 0.6669, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 1e-05, |
|
"loss": 0.5794, |
|
"step": 625 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 1e-05, |
|
"loss": 0.5546, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 1e-05, |
|
"loss": 0.5719, |
|
"step": 675 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 1e-05, |
|
"loss": 0.6211, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 1e-05, |
|
"loss": 0.5834, |
|
"step": 725 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 1e-05, |
|
"loss": 0.5279, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 1e-05, |
|
"loss": 0.4793, |
|
"step": 775 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 1e-05, |
|
"loss": 0.5624, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 1e-05, |
|
"loss": 0.4879, |
|
"step": 825 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 1e-05, |
|
"loss": 0.4641, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 1e-05, |
|
"loss": 0.5059, |
|
"step": 875 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 1e-05, |
|
"loss": 0.5037, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 1e-05, |
|
"loss": 0.4629, |
|
"step": 925 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 1e-05, |
|
"loss": 0.5116, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 1e-05, |
|
"loss": 0.5086, |
|
"step": 975 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 1e-05, |
|
"loss": 0.5555, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"eval_loss": 0.6125227212905884, |
|
"eval_runtime": 4223.437, |
|
"eval_samples_per_second": 3.55, |
|
"eval_steps_per_second": 0.222, |
|
"eval_wer": 53.84203447245193, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"step": 1000, |
|
"total_flos": 9.22665241903104e+18, |
|
"train_loss": 0.8689882726669311, |
|
"train_runtime": 7708.5213, |
|
"train_samples_per_second": 4.151, |
|
"train_steps_per_second": 0.13 |
|
} |
|
], |
|
"max_steps": 1000, |
|
"num_train_epochs": 9223372036854775807, |
|
"total_flos": 9.22665241903104e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|