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.

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

Stabilize MoE #16

Open
ClashLuke opened this issue Apr 30, 2022 · 0 comments
Open

Stabilize MoE #16

ClashLuke opened this issue Apr 30, 2022 · 0 comments
Labels
core Improves core model while keeping core idea intact engineering Software-engineering problems that don't require ML-Expertise ML Requires machine-learning knowledge (can be built up on the fly)

Comments

@ClashLuke
Copy link
Member

Currently, our MoE implementation leads to exploding losses and the eventual NaN.
This issue is about finding the cause behind these problems and fixing it.
@ClashLuke ClashLuke added engineering Software-engineering problems that don't require ML-Expertise ML Requires machine-learning knowledge (can be built up on the fly) labels Apr 30, 2022
@ClashLuke ClashLuke added the core Improves core model while keeping core idea intact label May 8, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
core Improves core model while keeping core idea intact engineering Software-engineering problems that don't require ML-Expertise ML Requires machine-learning knowledge (can be built up on the fly)
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@ClashLuke