learning_rate: 0.001
train_batch_size: 8
eval_batch_size: 8
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: 5
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Cer	Wer
1.1023	0.3419	200	0.7274	0.1928	0.5025
0.9531	0.6838	400	0.6376	0.1665	0.4613
0.8493	1.0256	600	0.5990	0.1583	0.4471
0.8849	1.3675	800	0.5687	0.1531	0.4267
0.8303	1.7094	1000	0.5544	0.1481	0.4195
0.8295	2.0513	1200	0.5455	0.1472	0.4177
0.8169	2.3932	1400	0.5352	0.1465	0.4181
0.7759	2.7350	1600	0.5332	0.1453	0.4129
0.838	3.0769	1800	0.5252	0.1420	0.4042
0.7476	3.4188	2000	0.5220	0.1415	0.4049
0.7028	3.7607	2200	0.5161	0.1404	0.4071
0.7355	4.1026	2400	0.5146	0.1408	0.3999
0.7489	4.4444	2600	0.5122	0.1399	0.4004
0.7108	4.7863	2800	0.5079	0.1382	0.3974

ctaguchi/ssc-sco-mms-model-mix-adapt-max

ssc-sco-mms-model-mix-adapt-max