# Impossible questions when finetuning QA models

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fimpossible-questions-when-finetuning-qa-models%2F12068%3E%5C
**Category:** 🤗Transformers\
**Created:** [November 19, 2021, 5:49pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fimpossible-questions-when-finetuning-qa-models%2F12068 "2021-11-19T17:49:21Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![erickrf](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/erickrf/32/239_2.png) [@erickrf](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Ferickrf)%5C
**Post date:** [November 19, 2021, 5:49pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fimpossible-questions-when-finetuning-qa-models%2F12068%2F1 "2021-11-19T17:49:21Z")

</div>

How can I encode impossible questions (i.e., without an answer in the context) when finetuning a QA model? I got a little confused with the code, not sure if giving start and end position as 0 (pointing to the `[CLS]` token) is the right approach.