# Deepset's bert cased trained on squad2 question

**URL:** <https://discuss.huggingface.co/t/deepsets-bert-cased-trained-on-squad2-question/42437>\
**Category:** Models\
**Created:** [June 7, 2023, 3:33pm UTC](https://discuss.huggingface.co/t/deepsets-bert-cased-trained-on-squad2-question/42437 "2023-06-07T15:33:33Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![llevkova](https://avatars.discourse-cdn.com/v4/letter/l/a88e4f/32.png) [@llevkova](https://discuss.huggingface.co/u/llevkova)\
**Post date:** [June 7, 2023, 3:33pm UTC](https://discuss.huggingface.co/t/deepsets-bert-cased-trained-on-squad2-question/42437/1 "2023-06-07T15:33:33Z")

</div>

This model has much higher F1/EM when evaluated on the validation squad2 data set than what is in the model card. Is the card outdated?