# T5: classification using text2text?

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ft5-classification-using-text2text%2F504%3E%5C
**Category:** 🤗Transformers\
**Created:** [July 28, 2020, 6:54pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ft5-classification-using-text2text%2F504 "2020-07-28T18:54:25Z")\
**Posts on this page:** 1\
**Showing post:** 10

<div class="post-metadata">

**Author:** ![BramVanroy](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/bramvanroy/32/47360_2.png) [@BramVanroy](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FBramVanroy)%5C
**Post date:** [June 18, 2021, 10:32am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ft5-classification-using-text2text%2F504%2F10 "2021-06-18T10:32:49Z")

</div>

Sorry for the topic steal, wasn’t getting a lot of attention on my topic on T5 ( [Yet another question about T5 prefixes: are they special? - Models - Hugging Face Forums](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fyet-another-question-about-t5-prefixes-are-they-special%2F6438)).

Has anyone here used T5 for regression? From the paper that @valhalla links, it seems that you could rebase your continuous labels to 0-1 and then use the output of the softmax for one of two options (e.g. true and false) in a MSELoss function. Or is that a nonsense suggestion? The caveat is that it is not always possible to rebase your values to 0-1.

---

_[View the full topic](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ft5-classification-using-text2text%2F504)._
