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: 4000
training_steps: 40000
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
0.1649	9.2173	2000	0.1052
0.1553	18.4347	4000	0.1013
0.1389	27.6520	6000	0.0997
0.1356	36.8694	8000	0.0967
0.1275	46.0832	10000	0.0954
0.1208	55.3006	12000	0.0950
0.1199	64.5179	14000	0.0934
0.1138	73.7353	16000	0.0943
0.1171	82.9526	18000	0.0933
0.1065	92.1665	20000	0.0924
0.1018	101.3838	22000	0.0927
0.0986	110.6012	24000	0.0916
0.1006	119.8185	26000	0.0912
0.0968	129.0324	28000	0.0914
0.0939	138.2497	30000	0.0908
0.0941	147.4671	32000	0.0904
0.0911	156.6844	34000	0.0911
0.0913	165.9017	36000	0.0905
0.0926	175.1156	38000	0.0905
0.0916	184.3329	40000	0.0904

sil-ai/senga-nt-fused-v3-tts

senga-nt-fused-v3-tts