learning_rate: 0.0001
train_batch_size: 4
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 8
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: linear
lr_scheduler_warmup_steps: 100
training_steps: 1000
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
0.4803	1.0312	100	0.4670
0.4797	2.0623	200	0.4720
0.4729	3.0935	300	0.4570
0.4713	4.1247	400	0.4545
0.4659	5.1558	500	0.4600
0.4565	6.1870	600	0.4545
0.4521	7.2182	700	0.4519
0.4514	8.2494	800	0.4569
0.438	9.2805	900	0.4512
0.4425	10.3117	1000	0.4529

PremZcoder/speecht5_finetuned_tamil_voice

speecht5_finetuned_tamil_voice