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: 22
num_epochs: 3.0
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
0.9819	0.3056	22	1.0092	35.2501
0.6106	0.6111	44	0.5360	23.8132
0.4364	0.9167	66	0.4371	20.8743
0.3996	1.2222	88	0.4085	18.9788
0.3957	1.5278	110	0.3959	19.2270
0.4241	1.8333	132	0.3881	19.2941
0.3595	2.1389	154	0.3838	18.6701
0.4155	2.4444	176	0.3794	18.6735
0.4105	2.75	198	0.3780	18.5024

greenw0lf/whisper-10hrs-random-seed333

whisper-10hrs-random-seed333