new parameter settings

[tztechno]

According to the recently published CPPO literature and GitHub, new unique parameter settings are used for CPPO.

https://arxiv.org/abs/2503.22342
https://github.com/lzhxmu/CPPO

Once open-r1 incorporates these into configs.py and grpo.py and standardizes them, it will be possible to verify the RL effectiveness of new combinations.