# Output of AdaptiveSoftmaxWithLoss

**URL:** <https://discuss.pytorch.org/t/output-of-adaptivesoftmaxwithloss/73792>\
**Category:** nlp\
**Created:** [March 19, 2020, 6:33pm UTC](https://discuss.pytorch.org/t/output-of-adaptivesoftmaxwithloss/73792 "2020-03-19T18:33:32Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Peyash](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/peyash/32/14251_2.png) [@Peyash](https://discuss.pytorch.org/u/Peyash)\
**Post date:** [March 19, 2020, 6:33pm UTC](https://discuss.pytorch.org/t/output-of-adaptivesoftmaxwithloss/73792/1 "2020-03-19T18:33:32Z")

</div>

I need help regarding `torch.nn.AdaptiveSoftmaxWithLoss`  
It returns both `output` and `loss`.  
`output` is the computed target log probabilities for each example, but I can’t seem to make sense of this.  
If it was a probability distribution over `C` classes then I could have predicted a particular class.  
How do I interpret this single target log probability? And what can I do with this?