Issues encountered during the evaluation

Im experiencing issues during evaluation. Have you encountered this? I reviewed your closed question and confirmed that training and sampling work normally in my environment. Could you help me analyze where the problem might be occurring? Thank you.

<img width="2525" height="960" alt="Image" src="https://github.com/user-attachments/assets/edf44236-ec67-4bce-bece-618ea74de2b4" />
