# Cross-validation for BERT models

**URL:** <https://discuss.huggingface.co/t/cross-validation-for-bert-models/2697>\
**Category:** 🤗Transformers\
**Created:** [December 8, 2020, 1:33pm UTC](https://discuss.huggingface.co/t/cross-validation-for-bert-models/2697 "2020-12-08T13:33:43Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Stimmot](https://avatars.discourse-cdn.com/v4/letter/s/46a35a/32.png) [@Stimmot](https://discuss.huggingface.co/u/Stimmot)\
**Post date:** [December 8, 2020, 1:33pm UTC](https://discuss.huggingface.co/t/cross-validation-for-bert-models/2697/1 "2020-12-08T13:33:43Z")

</div>

I was wondering whether there is any built-in way to use cross-validation on bert models for token classification. I scanned through the documentation but didn’t see anything resembling. Does anyone know a sample implementation of this feature?