learning_rate: 0.0005
train_batch_size: 1
eval_batch_size: 6
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 2
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: 5
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Cer	Wer
0.6953	0.2867	200	0.9526	0.2109	0.5338
0.7399	0.5735	400	0.9448	0.2104	0.5283
0.736	0.8602	600	0.8170	0.1996	0.5173
0.6204	1.1462	800	0.8343	0.2048	0.5133
0.77	1.4330	1000	0.9082	0.2060	0.5184
0.6475	1.7197	1200	0.7871	0.2086	0.5469
0.7394	2.0057	1400	0.8106	0.2012	0.5046
0.6703	2.2925	1600	0.8129	0.1991	0.4990
0.5731	2.5792	1800	0.7972	0.1989	0.5058
0.6649	2.8659	2000	0.7763	0.1940	0.4984
0.6588	3.1520	2200	0.8051	0.1953	0.4982
0.6042	3.4387	2400	0.7961	0.1877	0.4847
0.5617	3.7254	2600	0.7986	0.1898	0.4824
0.5678	4.0115	2800	0.7434	0.1900	0.4954
0.598	4.2982	3000	0.7335	0.1911	0.4956
0.5983	4.5849	3200	0.7530	0.1876	0.4861
0.5272	4.8717	3400	0.7720	0.1878	0.4832

ctaguchi/ssc-kcn-mms-model-mix-adapt-max3-devtrain

ssc-kcn-mms-model-mix-adapt-max3-devtrain