Evaluation results are inconsistent during training and after saving the trained model

[YUXIN-commit]

Hi MONAI Team,
First of all, thumbs up for your great work. I am facing the issue of inconsistent results of the SwinUNETR model while evaluating during the training and testing phases.
During training, I am getting good results but when I saved the pre-trained SwinUNETR model I am getting very bad results. I didn't change anything, just download your GitHub repo and trained the SwinUNETR model but the results are inconsistent. Here I am uploading the screenshots when I have trained the model for 100 epochs. Please help me to figure out the issue. Waiting for your response. Thank you in advance.

training results:

when I saved the pre-trained SwinUNETR model I am getting very bad results:

[YUXIN-commit]

I encountered another issue, which is 'Too many false positives on test-data' when using test.py. Has anyone encountered this problem before? Could you please let me know how to resolve it? "
Let me know if you'd like me to refine it further!

As shown in the image: