# Validation dataset and eras with non-zero targets

**URL:** <https://forum.numer.ai/t/validation-dataset-and-eras-with-non-zero-targets/5688>\
**Category:** Tournament\
**Created:** [September 10, 2022, 7:16pm UTC](https://forum.numer.ai/t/validation-dataset-and-eras-with-non-zero-targets/5688 "2022-09-10T19:16:38Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![henri\_toubon](https://avatars.discourse-cdn.com/v4/letter/h/ccd318/32.png) [@henri\_toubon](https://forum.numer.ai/u/henri_toubon)\
**Post date:** [September 10, 2022, 7:16pm UTC](https://forum.numer.ai/t/validation-dataset-and-eras-with-non-zero-targets/5688/1 "2022-09-10T19:16:38Z")

</div>

In the new validation dataset (333\_v4\_validation.parquet), the last era with non-zero target is 1020. It hasn’t changed since the previous week. Is there a reason why ?  
Thanks

---

<div class="post-metadata">

**Author:** ![taori](https://avatars.discourse-cdn.com/v4/letter/t/ebca7d/32.png) [@taori](https://forum.numer.ai/u/taori)\
**Post date:** [September 18, 2022, 4:09pm UTC](https://forum.numer.ai/t/validation-dataset-and-eras-with-non-zero-targets/5688/2 "2022-09-18T16:09:38Z")

</div>

I noticed the same “issue” few weeks ago, but not the same week as it happened to you. However the week later the targets were populated and I haven’t noticed the same behavior again.