训练过程问题 #286

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

Open

Why0912 opened this issue Jun 4, 2025 · 2 comments

Why0912 commented Jun 4, 2025

我在自己的构造的数据集训练过程中发现loss一直为0，同时训练时间也比较长，请问这是合理的吗？

Sammy20207109 commented Jun 7, 2025

same question

connorye commented Jun 10, 2025 •

edited

Loading

for me,the loss is keep 0.0 but 0.001 after 11 steps when finetune VLM-R1 with my custom refcoco dataset on 4 x A100 40G

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