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
0.2940	0.0945	50	0.2858	30.8939
0.2761	0.1890	100	0.2862	30.4842
0.2327	0.2836	150	0.2696	29.0689
0.2403	0.3781	200	0.2608	28.6965
0.2236	0.4726	250	0.2444	26.8529
0.2206	0.5671	300	0.2508	27.4115
0.2171	0.6616	350	0.2251	25.3631
0.2069	0.7561	400	0.2368	25.4190
0.1910	0.8507	450	0.2328	25.7169
0.1965	0.9452	500	0.2363	25.1955

dianavdavidson/wh_l_v3_t_fleurs_fleurs_52393__val_finetune_trial

wh_l_v3_t_fleurs_fleurs_52393__val_finetune_trial