learning_rate: 1e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
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: 25
num_epochs: 20
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
2.2761	1.0	42	1.1518	85.0	23.6036
0.6258	2.0	84	0.9264	58.75	18.1982
0.2154	3.0	126	0.9527	61.2500	18.1982
0.0842	4.0	168	0.9710	55.0000	16.5766
0.0357	5.0	210	1.0940	72.5	20.3604
0.0351	6.0	252	1.0147	70.0	18.0180
0.0120	7.0	294	1.0036	51.2500	16.0360
0.0047	8.0	336	1.1085	62.5	16.3964
0.0074	9.0	378	1.0849	55.0000	15.4955
0.0039	10.0	420	1.1564	65.0	17.4775
0.0009	11.0	462	1.1331	60.0	15.8559
0.0005	12.0	504	1.1476	60.0	15.8559
0.0004	13.0	546	1.1567	60.0	16.3964
0.0004	14.0	588	1.1608	60.0	16.3964
0.0003	15.0	630	1.1669	62.5	16.2162

thunderboltc/whisper-small-santali-sanlish-revised2_211sen

whisper-small-santali-sanlish-revised2_211sen