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
0.5805	0.0104	50	0.5219	43.3788
0.4222	0.0208	100	0.5044	35.9571
0.4767	0.0313	150	0.4454	34.8450
0.3600	0.0417	200	0.4487	36.8641
0.3748	0.0521	250	0.4258	47.2198
0.3724	0.0625	300	0.4281	37.0297
0.3890	0.0729	350	0.4175	52.0861
0.3425	0.0834	400	0.4024	34.5138
0.3268	0.0938	450	0.4033	76.9777
0.2691	0.1042	500	0.3831	36.2726

dianavdavidson/wh_l_v3_t_mucs_no_lg_id_mucs_52041_trial

wh_l_v3_t_mucs_no_lg_id_mucs_52041_trial