# Debugging a custom model at runtime

**URL:** <https://discuss.ray.io/t/debugging-a-custom-model-at-runtime/11442>\
**Category:** Debugging and performance tuning\
**Created:** [July 17, 2023, 7:38am UTC](https://discuss.ray.io/t/debugging-a-custom-model-at-runtime/11442 "2023-07-17T07:38:22Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Robert1](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/robert1/32/4766_2.png) [@Robert1](https://discuss.ray.io/u/Robert1)\
**Post date:** [July 17, 2023, 7:38am UTC](https://discuss.ray.io/t/debugging-a-custom-model-at-runtime/11442/1 "2023-07-17T07:38:22Z")

</div>

Hi everyone 👋  
I’m working on a custom model in a custom environment with ray rllib. Naturally, I need to debug frequently 🐛

Is there any good way to **debug a custom model during training**?  
The current behavior of ray rllib seems to be to deepcopy the model, which means breakpoints are not accessible right now.

Thanks everyone