It seems the result we get is not the same as the repo shows

[linbeyoung]

this is the result we get with the code in this repo. we follow the readme step by step, making sure the environment, model and requirement are the same with the repo, but we are puzzled that we can not have the same score, especially at about 4k-tokens where the score is very low. 我们使用仓库的源代码，模型和环境进行复现，得到的结果是上面这张图，想请问一下可能是哪里出现问题？