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
1.7805	0.0104	50	1.3156	61.5664
0.6200	0.0208	100	0.5134	40.9181
0.4913	0.0313	150	0.4462	39.6325
0.3551	0.0417	200	0.4287	33.6856
0.4245	0.0521	250	0.3990	38.1497
0.3450	0.0625	300	0.3913	42.4481
0.3726	0.0729	350	0.3765	47.1725
0.3265	0.0834	400	0.3662	33.3070
0.3109	0.0938	450	0.3473	45.4689
0.2556	0.1042	500	0.3412	38.1734

dianavdavidson/wh_med_mucs_no_lg_id_mucs_52041_trial

wh_med_mucs_no_lg_id_mucs_52041_trial