Is there any way to avoid overfitting while training over 200epoch?

[mightylg9094]

as written on title, I'm finding for the hints to avoid overfitting while training over 200epoch

I tried to change learning rate, but it didn't work

[Jun-Yan Zhu]

It seems that your learning rate has turned negative. This might cause the training failure.

[mightylg9094]

Thanks for the reply,

If you know, can you give me any clue about which parameter should I fix to avoid this?

[Jun-Yan Zhu]

You need to update your learning rate decay policy.