Clarification on Result Discrepancy Between Code and Paper Metrics

[en9t]

I hope this message finds you well. I have been following the instructions provided in the README of your code repository to reproduce the results from your paper, as part of my own research. However, I have encountered a discrepancy between the metrics I achieved and those reported in the paper.

Could you kindly clarify if there are any additional factors, modifications, or settings that I might have missed while running the code? I would appreciate any guidance you could provide to help me align my results with those presented in the paper.

Thank you for your time and assistance. I look forward to your response.

Best regards,

[en9t]

Sure! Here's the translation:

"Although there are a total of 1500 training rounds, the best performance is already achieved around the 300th round, and the following rounds just fluctuate without significant improvement."