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

Why don't we calculate the loss on the previous patch? #207

Open

fssqawj opened this issue Jan 2, 2025 · 0 comments

fssqawj commented Jan 2, 2025

timesfm/src/timesfm/patched_decoder.py

Line 532 in e77303c

def compute_loss(self, prediction_output: NestedMap,

I wonder why we don’t follow the loss calculation method of large language models and calculate the loss on the previous token.

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