learning_rate: 0.0001
train_batch_size: 8
eval_batch_size: 8
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: 1000
num_epochs: 30
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
5.0079	2.2321	500	3.3153	1.0
2.7173	4.4643	1000	1.8583	0.9674
1.6533	6.6964	1500	1.4112	0.8627
1.2519	8.9286	2000	1.2894	0.8331
1.0268	11.1607	2500	1.3173	0.7906
0.8764	13.3929	3000	1.3444	0.8009
0.7523	15.625	3500	1.3973	0.7838
0.663	17.8571	4000	1.4064	0.7877
0.5775	20.0893	4500	1.4676	0.7840
0.5175	22.3214	5000	1.5052	0.7707
0.469	24.5536	5500	1.5215	0.7618
0.4194	26.7857	6000	1.5784	0.7633
0.4031	29.0179	6500	1.5756	0.7689

akritidhasmana/wav2vec2-base-garhwali-demo-google-colab

wav2vec2-base-garhwali-demo-google-colab