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

Output same word #5

Open
dmuestc opened this issue Jun 27, 2024 · 2 comments
Open

Output same word #5

dmuestc opened this issue Jun 27, 2024 · 2 comments

Comments

@dmuestc
Copy link

dmuestc commented Jun 27, 2024

Hi, I download code and compile it, but got unexpected results.
environments:
OS: centos 7.5
GPU: V100, 32G
gcc: gcc-8

make -j 20
./runcuda "I have a dream"

The model outputs: "I have a dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream dream"

It's some weird.

@likejazz
Copy link
Owner

Unfortunately I don't have V100 so I can't test it, could you please print the whole logit value for debugging?

@dmuestc
Copy link
Author

dmuestc commented Jun 29, 2024

Reference in n

yes, I print the logits for the first five value, they are [0.019237, 0.026642, 0.019238, 0.019239, 0.019238], in line 821.
when generate function goes on, the logits keep all the same. It seems that the new token has not participate in generation process.
For each iteration, the largest prob value is always 0.176558, so the decoded token keeps "dream".
my cuda version is 12.2, gcc is 8.5.

I test the code in A100 GPU, CUDA 12.2, gcc 9.3, the result is the same.

Could you please show your compiler and gpu information, I try my best reprocess your results, thanks.

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