Adi

Results 6 comments of Adi

Getting NaN in Mel Loss during the first few epochs for first training

![Image](https://github.com/user-attachments/assets/a4c23af2-336e-4a46-bfba-267699b66812)

Getting NaN in Mel Loss during the first few epochs for first training

If I decrease the learning rate than it would lead to underfitted model

Getting NaN in Mel Loss during the first few epochs for first training

Here is tensorboard link http://151.115.73.7/

Getting NaN in Mel Loss during the first few epochs for first training

@yl4579

GPU memory error occurs at epoch 50 during phase first stage model training.

@kadirnar did you find a solution for this?

Consistently getting CUDNN_STATUS_INTERNAL_ERROR during second_stage training after diff_epoch

What batch size are you using? I am currently doing first training on two h100 and getting nan in mel loss? have you seen that when you did the first...