# Do\_eval, do\_predict difference

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fdo-eval-do-predict-difference%2F12814%3E%5C
**Category:** Beginners\
**Created:** [December 14, 2021, 2:16pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fdo-eval-do-predict-difference%2F12814 "2021-12-14T14:16:35Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![marcomatta](https://avatars.discourse-cdn.com/v4/letter/m/34f0e0/32.png) [@marcomatta](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fmarcomatta)%5C
**Post date:** [December 14, 2021, 2:16pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fdo-eval-do-predict-difference%2F12814%2F1 "2021-12-14T14:16:35Z")

</div>

Hi everyone! I’ve performed a NER task on a custom dataset (I got train, test and validation splits) but I’m confused by the “do\_eval” argument. Could someone explain me what’s the difference between do\_eval and do\_predict? Removing the eval\_dataset could affect the performance? Thanks in advance!