|
{ |
|
"best_metric": 28.265624367127064, |
|
"best_model_checkpoint": "./checkpoint-1000", |
|
"epoch": 0.14285714285714285, |
|
"global_step": 1000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 4.6000000000000004e-07, |
|
"loss": 1.4182, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 9.400000000000001e-07, |
|
"loss": 1.292, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.44e-06, |
|
"loss": 1.0018, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 1.94e-06, |
|
"loss": 0.7765, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 2.4400000000000004e-06, |
|
"loss": 0.7103, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 2.9400000000000002e-06, |
|
"loss": 0.6597, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 3.44e-06, |
|
"loss": 0.6657, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 3.94e-06, |
|
"loss": 0.5853, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 4.440000000000001e-06, |
|
"loss": 0.5273, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 4.94e-06, |
|
"loss": 0.5979, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 5.4400000000000004e-06, |
|
"loss": 0.5861, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 5.94e-06, |
|
"loss": 0.5085, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 6.440000000000001e-06, |
|
"loss": 0.4827, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 6.9400000000000005e-06, |
|
"loss": 0.4909, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 7.440000000000001e-06, |
|
"loss": 0.4651, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 7.94e-06, |
|
"loss": 0.494, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 8.44e-06, |
|
"loss": 0.4188, |
|
"step": 425 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 8.94e-06, |
|
"loss": 0.3849, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 9.440000000000001e-06, |
|
"loss": 0.4577, |
|
"step": 475 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 9.940000000000001e-06, |
|
"loss": 0.4415, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 9.966153846153847e-06, |
|
"loss": 0.4614, |
|
"step": 525 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 9.927692307692309e-06, |
|
"loss": 0.4283, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 9.88923076923077e-06, |
|
"loss": 0.4486, |
|
"step": 575 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 9.850769230769231e-06, |
|
"loss": 0.4434, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 9.812307692307694e-06, |
|
"loss": 0.4245, |
|
"step": 625 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 9.773846153846154e-06, |
|
"loss": 0.4254, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 9.735384615384616e-06, |
|
"loss": 0.4143, |
|
"step": 675 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 9.696923076923078e-06, |
|
"loss": 0.4115, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 9.658461538461539e-06, |
|
"loss": 0.3656, |
|
"step": 725 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 9.620000000000001e-06, |
|
"loss": 0.4004, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 9.581538461538462e-06, |
|
"loss": 0.388, |
|
"step": 775 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 9.543076923076924e-06, |
|
"loss": 0.3665, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 9.504615384615386e-06, |
|
"loss": 0.3777, |
|
"step": 825 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 9.466153846153846e-06, |
|
"loss": 0.4338, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 9.427692307692309e-06, |
|
"loss": 0.4017, |
|
"step": 875 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 9.38923076923077e-06, |
|
"loss": 0.3757, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 9.350769230769231e-06, |
|
"loss": 0.4084, |
|
"step": 925 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 9.312307692307693e-06, |
|
"loss": 0.3821, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 9.273846153846154e-06, |
|
"loss": 0.421, |
|
"step": 975 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 9.235384615384616e-06, |
|
"loss": 0.4203, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"eval_loss": 0.4127572178840637, |
|
"eval_runtime": 1802.5775, |
|
"eval_samples_per_second": 3.656, |
|
"eval_steps_per_second": 0.457, |
|
"eval_wer": 28.265624367127064, |
|
"step": 1000 |
|
} |
|
], |
|
"max_steps": 7000, |
|
"num_train_epochs": 9223372036854775807, |
|
"total_flos": 4.08241963008e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|