# Hyperparameter Tuning QNLI Colab Example using RoBERTa "RuntimeError('CUDA out of memory..."

**URL:** <https://discuss.huggingface.co/t/hyperparameter-tuning-qnli-colab-example-using-roberta-runtimeerror-cuda-out-of-memory/6270>\
**Category:** 🤗Transformers\
**Created:** [May 20, 2021, 1:27pm UTC](https://discuss.huggingface.co/t/hyperparameter-tuning-qnli-colab-example-using-roberta-runtimeerror-cuda-out-of-memory/6270 "2021-05-20T13:27:28Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![oqq09](https://avatars.discourse-cdn.com/v4/letter/o/f08c70/32.png) [@oqq09](https://discuss.huggingface.co/u/oqq09)\
**Post date:** [May 20, 2021, 1:27pm UTC](https://discuss.huggingface.co/t/hyperparameter-tuning-qnli-colab-example-using-roberta-runtimeerror-cuda-out-of-memory/6270/1 "2021-05-20T13:27:28Z")

</div>

![tunning_error](https://us1.discourse-cdn.com/hellohellohello/original/2X/3/34fb0ca50cc5bba102a664d426b60079aa5b85b6.png)  
I started from 10 trials and started lower the number every time I get the error. Can someone help with this error? Would it work if I had two GPUs working?

It seems no matter the number of trials, it crashes anyway at the last one.

Is there a way to free memory after each run?