learning_rate: 0.0003
train_batch_size: 8
eval_batch_size: 6
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
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: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Cer	Wer
1.1871	0.7648	200	0.8279	0.1866	0.6352
0.7886	1.5277	400	0.7769	0.1887	0.6419
0.7329	2.2906	600	0.7502	0.1785	0.6124
0.6881	3.0535	800	0.7380	0.1798	0.6157
0.647	3.8184	1000	0.7332	0.1798	0.6102
0.673	4.5813	1200	0.7311	0.1805	0.6145
0.5852	5.3442	1400	0.7352	0.1780	0.6076
0.6142	6.1071	1600	0.7315	0.1774	0.6054
0.6056	6.8719	1800	0.7371	0.1778	0.6061
0.6021	7.6348	2000	0.7350	0.1772	0.6072
0.5971	8.3977	2200	0.7379	0.1787	0.6102
0.5732	9.1606	2400	0.7342	0.1762	0.6020
0.5988	9.9254	2600	0.7360	0.1766	0.6035

ctaguchi/ssc-tob-mms-model-mix-adapt-max-lowlr

ssc-tob-mms-model-mix-adapt-max-lowlr