|
{ |
|
"best_metric": 15.385478912645503, |
|
"best_model_checkpoint": "./checkpoint-1000", |
|
"epoch": 1.187, |
|
"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-07, |
|
"loss": 1.6724, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 9.400000000000001e-07, |
|
"loss": 1.2152, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 1.44e-06, |
|
"loss": 0.5589, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 1.94e-06, |
|
"loss": 0.2506, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 2.4400000000000004e-06, |
|
"loss": 0.1692, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 2.9400000000000002e-06, |
|
"loss": 0.1603, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 3.44e-06, |
|
"loss": 0.1213, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 3.94e-06, |
|
"loss": 0.1053, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 4.440000000000001e-06, |
|
"loss": 0.1164, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 4.94e-06, |
|
"loss": 0.0893, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 5.4400000000000004e-06, |
|
"loss": 0.0793, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 5.94e-06, |
|
"loss": 0.0636, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 6.440000000000001e-06, |
|
"loss": 0.0823, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 6.9400000000000005e-06, |
|
"loss": 0.0754, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 7.440000000000001e-06, |
|
"loss": 0.0694, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 7.94e-06, |
|
"loss": 0.0672, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 8.44e-06, |
|
"loss": 0.0512, |
|
"step": 425 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 8.94e-06, |
|
"loss": 0.0434, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 9.440000000000001e-06, |
|
"loss": 0.0396, |
|
"step": 475 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 9.940000000000001e-06, |
|
"loss": 0.0504, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 9.56e-06, |
|
"loss": 0.0578, |
|
"step": 525 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 9.060000000000001e-06, |
|
"loss": 0.0555, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 8.560000000000001e-06, |
|
"loss": 0.0501, |
|
"step": 575 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 8.06e-06, |
|
"loss": 0.0636, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 7.5600000000000005e-06, |
|
"loss": 0.0614, |
|
"step": 625 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 7.06e-06, |
|
"loss": 0.0559, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 6.560000000000001e-06, |
|
"loss": 0.0539, |
|
"step": 675 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 6.0600000000000004e-06, |
|
"loss": 0.0453, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 5.560000000000001e-06, |
|
"loss": 0.0422, |
|
"step": 725 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 5.060000000000001e-06, |
|
"loss": 0.0356, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 4.56e-06, |
|
"loss": 0.0464, |
|
"step": 775 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 4.060000000000001e-06, |
|
"loss": 0.0487, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 3.5600000000000002e-06, |
|
"loss": 0.0578, |
|
"step": 825 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 3.0600000000000003e-06, |
|
"loss": 0.064, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 2.56e-06, |
|
"loss": 0.0576, |
|
"step": 875 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 2.06e-06, |
|
"loss": 0.0419, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 1.56e-06, |
|
"loss": 0.0403, |
|
"step": 925 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 1.06e-06, |
|
"loss": 0.0399, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 5.6e-07, |
|
"loss": 0.033, |
|
"step": 975 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 6.000000000000001e-08, |
|
"loss": 0.0301, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"eval_loss": 0.2696547210216522, |
|
"eval_runtime": 16787.919, |
|
"eval_samples_per_second": 1.208, |
|
"eval_steps_per_second": 0.038, |
|
"eval_wer": 15.385478912645503, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"step": 1000, |
|
"total_flos": 6.528095169970176e+19, |
|
"train_loss": 0.15153720045089722, |
|
"train_runtime": 34913.8382, |
|
"train_samples_per_second": 1.833, |
|
"train_steps_per_second": 0.029 |
|
} |
|
], |
|
"max_steps": 1000, |
|
"num_train_epochs": 9223372036854775807, |
|
"total_flos": 6.528095169970176e+19, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|