learning_rate: 0.001
train_batch_size: 4
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 100
num_epochs: 2
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
4.5289	0.1976	100	0.7768	0.7000
0.8566	0.3953	200	0.6045	0.6389
0.7329	0.5929	300	0.5343	0.5567
0.7219	0.7905	400	0.4980	0.5359
0.6556	0.9881	500	0.4649	0.5202
0.5582	1.1858	600	0.4556	0.5060
0.5591	1.3834	700	0.4280	0.4818
0.5100	1.5810	800	0.4058	0.4652
0.5390	1.7787	900	0.3901	0.4479
0.5154	1.9763	1000	0.3846	0.4456

pisethchan/trainer_output

trainer_output