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.

Sign up for GitHub

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

Jump to bottom

bug 计算sft损失的时候 #48

Open

shyoulala opened this issue Nov 24, 2023 · 2 comments

shyoulala commented Nov 24, 2023

计算sft损失的时候label和logits貌似没有shift，是我理解有问题吗？
应该是new_logits = logits[:,:-1,:]

Author

shyoulala commented Nov 24, 2023

这样：

Owner

GanjinZero commented Nov 24, 2023

labels在DataCollatorForSupervisedDataset里shift过了

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment