learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 153
num_epochs: 25
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
3.4164	1.0	103	0.6553	44.3325	10.3516
0.9734	2.0	206	0.5723	38.7909	8.9410
0.4124	3.0	309	0.5563	38.0353	8.3984
0.1842	4.0	412	0.5620	35.8942	7.8993
0.1116	5.0	515	0.5717	33.8791	7.8993
0.0794	6.0	618	0.5897	34.1310	7.8125
0.0470	7.0	721	0.6306	34.8866	7.8776
0.0363	8.0	824	0.6719	35.1385	7.8993
0.0266	9.0	927	0.6565	35.5164	7.9210
0.0132	10.0	1030	0.6691	34.5088	7.6606

thunderboltc/whisper-small-santali-sanlish-1934

whisper-small-santali-sanlish-1934