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
0.6510	0.0133	50	0.5022	28.5954
0.4194	0.0266	100	0.3550	36.9255
0.4357	0.0399	150	0.2932	111.3950
0.3501	0.0531	200	0.2691	128.4799
0.2382	0.0664	250	0.2580	177.8221
0.2971	0.0797	300	0.2487	250.0523
0.2500	0.0930	350	0.2460	230.3838
0.2935	0.1063	400	0.2423	342.3452
0.2283	0.1196	450	0.2502	285.3897
0.2770	0.1329	500	0.2322	294.4452

dianavdavidson/wh_l_v3_mucs_30_70_flattened_mucs_52553__val_finetune_trial

wh_l_v3_mucs_30_70_flattened_mucs_52553__val_finetune_trial