train issue

[zxy951005]

Hi, shayneobrien:
I'am Xiangyu from China, I have some quetions about your code. I used your code, but when I am training, the loss has not been descent. I have checked the code several times. The recall ande the precison is almost zero.
Best wish!

[QingLIU67]

Agree, my loss doesn't converge either.

[VishwaasHegde]

I have the same issue too. The precision and recall are almost always zero, also the probs is tensor of only 1s' (with padding).