learning_rate: 0.0003
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
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: 500
num_epochs: 12
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
No log	0.7859	200	3.4577	1.0	1.0
12.8852	1.5697	400	2.5259	1.0	0.7353
12.8852	2.3536	600	1.0384	0.8125	0.2773
2.4385	3.1375	800	0.8222	0.6533	0.2156
2.4385	3.9234	1000	0.7358	0.5958	0.1898
1.2812	4.7073	1200	0.7123	0.5749	0.1791
1.2812	5.4912	1400	0.7409	0.5552	0.1728
0.7982	6.2750	1600	0.7872	0.5438	0.1703
0.7982	7.0589	1800	0.8121	0.5399	0.1693
0.4679	7.8448	2000	0.8149	0.5356	0.1675
0.4679	8.6287	2200	0.8744	0.5244	0.1646
0.2934	9.4126	2400	0.9256	0.5176	0.1623
0.2934	10.1965	2600	0.9820	0.5158	0.1617
0.2009	10.9823	2800	0.9721	0.5127	0.1616
0.2009	11.7662	3000	0.9987	0.5076	0.1600

Muzaffar786/wav2vec2-kashmiri-full-data

wav2vec2-kashmiri-full-data