Something wrong when computing loss

[llipa]

It goes wrong when computing loss in losses.py point_loss_ = self._point_loss(logits, pos.squeeze(1)) And I check the value of logits and pos The shape of logits is (64,42), pos (64,1)

[llipa]

Is there anything wrong with these two matrix?

[Jinx630]

Is there anything wrong with these two matrix?

I have the same problem. Have you solved it?

[YFCodeDream]

I also met this problem. Do you have any solution? These two variables can't get the correct result of the CrossEntropyLoss.