Why the lose value is Nan at the beginning of training sometimes？

[Lzyin]

Describe the bug A clear and concise description of what the bug is.

To Reproduce Steps to reproduce the behavior (e.g. the command that you used).

Expected behavior A clear and concise description of what you expected to happen.

Desktop (please complete the following information):

• OS: [e.g. Linux/Windows]
• CUDA : yes/no

[nshaud]

With what parameters? Can you give some more details to reproduce this problem?