graykode / xlnet-Pytorch

Simple XLNet implementation with Pytorch Wrapper

Home Page:https://arxiv.org/pdf/1906.08237.pdf

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Low accuracy on sample task

ndalton12 opened this issue · comments

Hi author,

Any idea why the performance accuracy is so low on the sample task you provide?

I added the following lines to test accuracy:
output = logits.transpose(1, 2)
predicts = F.softmax(output, dim=1).argmax(dim=1)
print((predicts == target).sum().item() / len(target))

The accuracy for the task is ~0.01% after 100 epochs.

I think it is not important accuracy in this domain