learning_rate: 1e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 16
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: 50
num_epochs: 5

Training Loss	Epoch	Step	Cer	Validation Loss	Wer
1.4182	0.5674	10	0.1771	1.3644	0.3574
1.3081	1.1135	20	0.1771	1.3655	0.3574
1.4107	1.6809	30	0.1771	1.3661	0.3574
1.4016	2.2837	40	0.1813	1.3622	0.3688
1.3979	2.7943	50	0.1820	1.3586	0.3688
1.4308	3.3972	60	1.3539
1.3849	3.9645	70	1.3514
1.2477	4.5106	80	1.3484

Jeff13680/whisper-lora-640

whisper-lora-640