train ConvolutionModel model,it seems failed

[snowlord]

when i train CNN model,it epochs 2 twice ,the loss value became nan. it seems getting in local minmize.

[metalaman]

I've ported the CNN-LSTM model implemented here, on PyTorch and my loss also becomes 0.0 for the second, third and fourth epochs and then rises again and keeps oscillating. Is it a Learning Rate issue.