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
0.6983	0.2658	200	0.5624	0.1404	0.4446
0.6518	0.5316	400	0.5353	0.1406	0.4348
0.5823	0.7973	600	0.5431	0.1381	0.4301
0.573	1.0625	800	0.5462	0.1382	0.4358
0.6338	1.3282	1000	0.5299	0.1370	0.4257
0.5693	1.5940	1200	0.5296	0.1369	0.4292
0.5789	1.8598	1400	0.5216	0.1366	0.4249
0.5366	2.1249	1600	0.5204	0.1388	0.4340
0.518	2.3907	1800	0.5237	0.1360	0.4219
0.6573	2.6565	2000	0.5170	0.1346	0.4158
0.557	2.9223	2200	0.5187	0.1356	0.4189
0.5135	3.1874	2400	0.5164	0.1352	0.4182
0.4979	3.4532	2600	0.5103	0.1349	0.4168
0.5908	3.7189	2800	0.5137	0.1350	0.4175
0.553	3.9847	3000	0.5103	0.1351	0.4172
0.5559	4.2498	3200	0.5115	0.1352	0.4184
0.5706	4.5156	3400	0.5094	0.1347	0.4169
0.5647	4.7814	3600	0.5083	0.1348	0.4147

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

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