Pytorch Cnn Model Stop At Loss.backward() Without Any Prompt?

My aim is to make a five-category text classification I am running bert fine tuning with cnnbase model but my project stops at loss.backward() without any prompt in cmd. My program

Solution 1:

I tried to run my program on linux platform, and it ran successfully.

Therefore, it is very likely that it is caused by different os

Previous os：win 10

Solution 2:

I also met the same problem. And in my case, this issue originated from of pytorch's version compatibility. Issue got resolved when I upgraded my pytorch to newest release(1.5.1 -> 1.8.x). I think this kind of issue came from pytorch's nn.Conv class... since I found my script running well when I removed them.