|
{ |
|
"best_metric": 10.503340419070756, |
|
"best_model_checkpoint": "./checkpoint-1000", |
|
"epoch": 3.052, |
|
"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": 4.6000000000000004e-07, |
|
"loss": 1.0986, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 9.600000000000001e-07, |
|
"loss": 0.8438, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 1.46e-06, |
|
"loss": 0.2768, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 1.9600000000000003e-06, |
|
"loss": 0.1883, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 2.46e-06, |
|
"loss": 0.1602, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 2.96e-06, |
|
"loss": 0.1401, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 3.46e-06, |
|
"loss": 0.1456, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 3.96e-06, |
|
"loss": 0.1446, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 4.4600000000000005e-06, |
|
"loss": 0.1658, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 4.960000000000001e-06, |
|
"loss": 0.1517, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 5.460000000000001e-06, |
|
"loss": 0.1521, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 5.9600000000000005e-06, |
|
"loss": 0.1309, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 6.460000000000001e-06, |
|
"loss": 0.1455, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 6.96e-06, |
|
"loss": 0.1544, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 7.4600000000000006e-06, |
|
"loss": 0.1497, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 7.960000000000002e-06, |
|
"loss": 0.1058, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 8.46e-06, |
|
"loss": 0.0996, |
|
"step": 425 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 8.96e-06, |
|
"loss": 0.0982, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 9.460000000000001e-06, |
|
"loss": 0.0868, |
|
"step": 475 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 9.960000000000001e-06, |
|
"loss": 0.0915, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 9.54e-06, |
|
"loss": 0.0926, |
|
"step": 525 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 9.040000000000002e-06, |
|
"loss": 0.0926, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 8.540000000000001e-06, |
|
"loss": 0.0792, |
|
"step": 575 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 8.040000000000001e-06, |
|
"loss": 0.0802, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 7.540000000000001e-06, |
|
"loss": 0.0754, |
|
"step": 625 |
|
}, |
|
{ |
|
"epoch": 2.02, |
|
"learning_rate": 7.04e-06, |
|
"loss": 0.0741, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 2.04, |
|
"learning_rate": 6.540000000000001e-06, |
|
"loss": 0.075, |
|
"step": 675 |
|
}, |
|
{ |
|
"epoch": 2.07, |
|
"learning_rate": 6.040000000000001e-06, |
|
"loss": 0.0645, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 2.09, |
|
"learning_rate": 5.540000000000001e-06, |
|
"loss": 0.055, |
|
"step": 725 |
|
}, |
|
{ |
|
"epoch": 2.12, |
|
"learning_rate": 5.04e-06, |
|
"loss": 0.0482, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 2.14, |
|
"learning_rate": 4.540000000000001e-06, |
|
"loss": 0.0415, |
|
"step": 775 |
|
}, |
|
{ |
|
"epoch": 2.17, |
|
"learning_rate": 4.04e-06, |
|
"loss": 0.0442, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 2.19, |
|
"learning_rate": 3.54e-06, |
|
"loss": 0.0441, |
|
"step": 825 |
|
}, |
|
{ |
|
"epoch": 2.22, |
|
"learning_rate": 3.04e-06, |
|
"loss": 0.0415, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 2.24, |
|
"learning_rate": 2.5400000000000002e-06, |
|
"loss": 0.0356, |
|
"step": 875 |
|
}, |
|
{ |
|
"epoch": 2.27, |
|
"learning_rate": 2.04e-06, |
|
"loss": 0.0306, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 2.29, |
|
"learning_rate": 1.54e-06, |
|
"loss": 0.0317, |
|
"step": 925 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 1.04e-06, |
|
"loss": 0.0348, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 3.03, |
|
"learning_rate": 5.4e-07, |
|
"loss": 0.0322, |
|
"step": 975 |
|
}, |
|
{ |
|
"epoch": 3.05, |
|
"learning_rate": 4e-08, |
|
"loss": 0.0348, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 3.05, |
|
"eval_loss": 0.18787039816379547, |
|
"eval_runtime": 2768.6707, |
|
"eval_samples_per_second": 3.663, |
|
"eval_steps_per_second": 0.229, |
|
"eval_wer": 10.503340419070756, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 3.05, |
|
"step": 1000, |
|
"total_flos": 6.54105685229568e+19, |
|
"train_loss": 0.14094245743751527, |
|
"train_runtime": 15142.1641, |
|
"train_samples_per_second": 4.227, |
|
"train_steps_per_second": 0.066 |
|
} |
|
], |
|
"max_steps": 1000, |
|
"num_train_epochs": 9223372036854775807, |
|
"total_flos": 6.54105685229568e+19, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|