# 0 gpu usage on textcat-multilabel

**URL:** <https://support.prodi.gy/t/0-gpu-usage-on-textcat-multilabel/7230>\
**Category:** Uncategorized\
**Created:** [May 17, 2024, 11:58am UTC](https://support.prodi.gy/t/0-gpu-usage-on-textcat-multilabel/7230 "2024-05-17T11:58:32Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![punctal](https://avatars.discourse-cdn.com/v4/letter/p/f0a364/32.png) [@punctal](https://support.prodi.gy/u/punctal)\
**Post date:** [May 17, 2024, 11:58am UTC](https://support.prodi.gy/t/0-gpu-usage-on-textcat-multilabel/7230/1 "2024-05-17T11:58:32Z")

</div>

I have classified 1k examples with:

prodigy textcat.teach textcat\_spam blank:en ./input.jsonl --label SPAM --patterns ./spam-patterns.jsonl

and then tried to run:

prodigy train spam-classifier-v2 --textcat-multilabel textcat\_spam --eval-split 0.2 --lang en --gpu-id 1

which complained about cupy not being installed so I installed it (cuda 12.3 on host, so cuda12x package)

it still is only training on one CPU core, why? thanks

---

<div class="post-metadata">

**Author:** ![magdaaniol](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/magdaaniol/32/2787_2.png) [@magdaaniol](https://support.prodi.gy/u/magdaaniol)\
**Post date:** [May 20, 2024, 11:05am UTC](https://support.prodi.gy/t/0-gpu-usage-on-textcat-multilabel/7230/2 "2024-05-20T11:05:51Z")

</div>

Welcome to the forum @punctal !

Could you please run your `train` command with `PRODIGY_LOGGING=basic` and share the stdout please?  
The commands look correct to me.