learning_rate: 0.0005
train_batch_size: 8
eval_batch_size: 6
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH 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: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Cer	Wer
4.7441	0.6700	200	4.5692	0.8499	1.0
3.1454	1.3384	400	2.8762	0.8834	1.0
2.8759	2.0067	600	2.7991	0.8939	1.0
2.7927	2.6767	800	2.7170	0.8714	1.0
2.6427	3.3451	1000	2.5878	0.8401	1.0046
2.6826	4.0134	1200	2.6477	0.9101	1.0
2.6617	4.6834	1400	2.5153	0.8783	1.0
2.5807	5.3518	1600	2.4798	0.8144	1.0055
2.5083	6.0201	1800	2.4124	0.8721	1.0
2.5154	6.6901	2000	2.3597	0.8803	1.0
2.7958	7.3585	2200	2.7983	0.9183	1.0
2.7276	8.0268	2400	2.5911	0.9095	1.0
2.649	8.6968	2600	2.5195	0.8957	1.0
2.5892	9.3652	2800	2.4935	0.8858	1.0

ctaguchi/ssc-qxp-mms-model-mix-adapt-max3

ssc-qxp-mms-model-mix-adapt-max3