learning_rate: 0.0001
train_batch_size: 8
eval_batch_size: 8
seed: 3407
gradient_accumulation_steps: 4
total_train_batch_size: 32
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: cosine
lr_scheduler_warmup_steps: 2000
training_steps: 20000
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
0.0933	90.9091	1000	0.0817
0.076	181.8182	2000	0.0809
0.0629	272.7273	3000	0.0836
0.0599	363.6364	4000	0.0844
0.0559	454.5455	5000	0.0894
0.0511	545.4545	6000	0.0913
0.0478	636.3636	7000	0.0950
0.0436	727.2727	8000	0.0971
0.045	818.1818	9000	0.0973
0.0407	909.0909	10000	0.1029
0.0395	1000.0	11000	0.1021
0.0409	1090.9091	12000	0.1015
0.0372	1181.8182	13000	0.1045
0.038	1272.7273	14000	0.1031
0.0356	1363.6364	15000	0.1075
0.0369	1454.5455	16000	0.1048
0.0362	1545.4545	17000	0.1046
0.0421	1636.3636	18000	0.1072
0.0364	1727.2727	19000	0.1068
0.0381	1818.1818	20000	0.1049

sil-ai/senga-LUK-20k-clean-speecht5

senga-LUK-20k-clean-speecht5