Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

关于Chatglm的ppl #75

Open
hxsz1997 opened this issue Feb 1, 2024 · 1 comment
Open

关于Chatglm的ppl #75

hxsz1997 opened this issue Feb 1, 2024 · 1 comment

Comments

@hxsz1997
Copy link

hxsz1997 commented Feb 1, 2024

我使用bash bash_scripts/skywork_eval_loss.sh来评估chatglm3-6b在zh_general.jsonl上的ppl,结果是42.0536,和论文中提供的结果(7.47)不一致。评估chatglm2-6b在zh_general.jsonl上的ppl,结果是inf

@zhao1iang
Copy link
Collaborator

无论是42还是Inf都不是一个正常的值。这个似乎是模型参数没有加载正确导致参数是随机的,或者tokenizer不对,您可以检查下模型加载是否正确,是否能正常的根据prompt进行输出。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants