learning_rate: 0.0001
train_batch_size: 48
eval_batch_size: 32
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 53
num_epochs: 3.0
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
0.5879	0.2994	53	0.5379	25.9838
0.4106	0.5989	106	0.3838	18.0193
0.3296	0.8983	159	0.3624	17.4556
0.3091	1.1977	212	0.3492	16.2814
0.321	1.4972	265	0.3424	16.5062
0.3195	1.7966	318	0.3339	15.3689
0.2962	2.0960	371	0.3314	15.3991
0.3024	2.3955	424	0.3305	15.2347
0.2938	2.6949	477	0.3277	14.8858
0.2834	2.9944	530	0.3261	15.0502

greenw0lf/whisper-20hrs-class-seed42

whisper-20hrs-class-seed42