Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
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

Chameleon stability experiments #616

Merged
merged 106 commits into from
Jul 17, 2024
Merged

Chameleon stability experiments #616

merged 106 commits into from
Jul 17, 2024

Conversation

AkshitaB
Copy link
Contributor

@AkshitaB AkshitaB commented Jun 11, 2024 •
edited
Loading

Main changes:

Norm reordering (norm_after config option).
The zloss multiplier is now configurable (auxiliary_loss_multiplier config option).

@AkshitaB AkshitaB marked this pull request as ready for review July 16, 2024 18:38
@AkshitaB AkshitaB requested a review from epwalsh July 16, 2024 18:41
epwalsh
epwalsh requested changes Jul 16, 2024
View reviewed changes
Copy link
Member

@epwalsh epwalsh left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks good overall, only minor comments

olmo/train.py Outdated Show resolved Hide resolved
olmo/model.py Show resolved Hide resolved
CHANGELOG.md Outdated Show resolved Hide resolved
epwalsh
epwalsh reviewed Jul 17, 2024
View reviewed changes
tests/fused_loss_test.py Outdated Show resolved Hide resolved
tests/fused_loss_test.py Outdated Show resolved Hide resolved
@AkshitaB AkshitaB requested a review from epwalsh July 17, 2024 21:03
@AkshitaB AkshitaB merged commit dfb7212 into main Jul 17, 2024
12 checks passed
@AkshitaB AkshitaB deleted the chameleon branch July 17, 2024 21:22
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@epwalsh epwalsh epwalsh approved these changes

@dirkgr dirkgr Awaiting requested review from dirkgr

@2015aroras 2015aroras Awaiting requested review from 2015aroras

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@AkshitaB @epwalsh