# Loss Increases But Metrics Get Better?

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Floss-increases-but-metrics-get-better%2F52552%3E%5C
**Category:** Beginners\
**Created:** [August 28, 2023, 9:42pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Floss-increases-but-metrics-get-better%2F52552 "2023-08-28T21:42:05Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Yuti](https://avatars.discourse-cdn.com/v4/letter/y/cdc98d/32.png) [@Yuti](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FYuti)%5C
**Post date:** [August 28, 2023, 9:42pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Floss-increases-but-metrics-get-better%2F52552%2F1 "2023-08-28T21:42:05Z")

</div>

Hi 😄  
I was experimenting with the [Token Classification Example Notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/transformers_doc/en/pytorch/token_classification.ipynb) and encountered something odd.

This notebook fine-tunes DistilBERT on the WNUT-17 dataset. I have increased the original 2 training epochs up to 10 and the results are as follows:

 ![image](https://us1.discourse-cdn.com/hellohellohello/original/3X/d/4/d420597f42b7583a1f5cd1837e909e130fb3fcf4.png)

As can be seen from the picture above, during the fine-tuning process the **validation** loss increases (probably a case of over-fitting) while the metrics improve.

Can someone explain this phenomenon?

Thanks!