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
0.3264	0.4739	200	0.9296	0.1810	0.8401
0.3411	0.9479	400	0.9353	0.1776	0.8480
0.2961	1.4218	600	0.9733	0.1791	0.8408
0.3263	1.8957	800	0.9891	0.1707	0.8281
0.2613	2.3697	1000	1.0369	0.1749	0.8384
0.2602	2.8436	1200	1.0332	0.1712	0.8317
0.2309	3.3175	1400	1.0195	0.1725	0.8274
0.236	3.7915	1600	1.0189	0.1723	0.8354
0.2158	4.2654	1800	1.0199	0.1717	0.8276
0.2128	4.7393	2000	1.0191	0.1685	0.8244

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

ssc-hch-mms-model-mix-adapt-max3