learning_rate: 0.0003
train_batch_size: 1
eval_batch_size: 6
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 2
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: 5
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Cer	Wer
0.2723	0.2789	200	0.1972	0.0708	0.4000
0.2445	0.5579	400	0.1970	0.0754	0.4108
0.2361	0.8368	600	0.1942	0.0744	0.4055
0.2245	1.1158	800	0.1927	0.0709	0.3989
0.2219	1.3947	1000	0.1930	0.0711	0.4044
0.2404	1.6736	1200	0.1862	0.0698	0.3934
0.2779	1.9526	1400	0.1840	0.0696	0.3910
0.2132	2.2315	1600	0.1864	0.0693	0.3927
0.2173	2.5105	1800	0.1811	0.0689	0.3861
0.2019	2.7894	2000	0.1850	0.0695	0.3863
0.2098	3.0683	2200	0.1819	0.0680	0.3851
0.196	3.3473	2400	0.1836	0.0682	0.3892
0.2333	3.6262	2600	0.1811	0.0682	0.3870
0.2336	3.9052	2800	0.1808	0.0679	0.3837
0.2226	4.1841	3000	0.1806	0.0678	0.3831
0.2016	4.4630	3200	0.1793	0.0677	0.3831
0.1872	4.7420	3400	0.1796	0.0677	0.3825

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

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