# Issues with Finetuning QuestionAnswer model

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fissues-with-finetuning-questionanswer-model%2F6432%3E%5C
**Category:** Beginners\
**Created:** [May 27, 2021, 5:45pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fissues-with-finetuning-questionanswer-model%2F6432 "2021-05-27T17:45:08Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![MLSAG](https://avatars.discourse-cdn.com/v4/letter/m/db5fbb/32.png) [@MLSAG](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FMLSAG)%5C
**Post date:** [May 27, 2021, 5:45pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fissues-with-finetuning-questionanswer-model%2F6432%2F1 "2021-05-27T17:45:08Z")

</div>

Hi ,

I am attempting to finetune a QuestionAnswer model (distilbert) using this [example](https://github.com/huggingface/notebooks/blob/master/examples/question_answering.ipynb) with a custom dataset with long contexts. For this attempt I have used small data set ~ 1000 records. This is my first such attempt; please forgive me if this is a very basic question.

I have saved the model and the PreTrainedTokenizerFast tokenizer. But when I use the saved model and tokenizer, I do not get any predictions. Following is my code for

 ![image](https://us1.discourse-cdn.com/hellohellohello/original/2X/1/122ee94d8e249bb1980f613dc4c471d220e7f9d6.png)

Can someone please help me understand what I am doing wrong?