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
0.6858	0.0945	50	0.5513	54.9721
0.4892	0.1890	100	0.4495	46.2756
0.3921	0.2836	150	0.4028	43.5009
0.3918	0.3781	200	0.3814	41.8250
0.3594	0.4726	250	0.3621	40.2048
0.3263	0.5671	300	0.3467	40.6704
0.3102	0.6616	350	0.3314	41.3222
0.3000	0.7561	400	0.3277	41.5642
0.2899	0.8507	450	0.3166	40.5959
0.2748	0.9452	500	0.3062	41.5084

dianavdavidson/wh_small_fleurs_no_lg_id_fleurs_52395__val_finetune_trial

wh_small_fleurs_no_lg_id_fleurs_52395__val_finetune_trial