learning_rate: 5e-06
train_batch_size: 4
eval_batch_size: 4
seed: 42
optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant_with_warmup
lr_scheduler_warmup_steps: 50
training_steps: 500

Training Loss	Epoch	Step	Validation Loss	Global Wer
0.6992	0.0158	50	0.5604	37.7954
0.3589	0.0317	100	0.3378	36.8289
0.3320	0.0475	150	0.2995	37.8657
0.3566	0.0633	200	0.2780	67.3798
0.2967	0.0792	250	0.2751	42.9004
0.2719	0.0950	300	0.2573	97.9220
0.2528	0.1108	350	0.2617	79.2198
0.2488	0.1267	400	0.2501	116.2244
0.2372	0.1425	450	0.2452	131.2231
0.2545	0.1583	500	0.2492	75.1252

dianavdavidson/wh_l_v3_iv_30_70_indic_voices_52508__val_finetune_trial

wh_l_v3_iv_30_70_indic_voices_52508__val_finetune_trial