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

First approximation to a DASM: 20 output dimensions but same loss #64

Merged
merged 18 commits into from
Oct 14, 2024
Merged

First approximation to a DASM: 20 output dimensions but same loss #64

merged 18 commits into from
Oct 14, 2024

Conversation

matsen
Copy link
Contributor

@matsen matsen commented Oct 3, 2024 •
edited
Loading

  • Adding output_dim option to DNSM
  • refactoring DNSMDataset methods to be subclass-friendly
  • adding conftest for shared fixtures
  • generalizing branch length optimization

@matsen matsen linked an issue Oct 3, 2024 that may be closed by this pull request
DASM approximation 1: use higher-dimensional output of a DNSM, but train in the same way #63
Closed
@matsen matsen requested a review from willdumm October 14, 2024 16:26
willdumm
willdumm approved these changes Oct 14, 2024
View reviewed changes
Copy link
Contributor

@willdumm willdumm left a comment

Choose a reason for hiding this comment

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

Looks great to me!

@matsen matsen merged commit ac86175 into main Oct 14, 2024
1 check passed
@matsen matsen deleted the 63-dasm-approx branch October 14, 2024 20:44
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@willdumm willdumm willdumm approved these changes

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

Successfully merging this pull request may close these issues.

DASM approximation 1: use higher-dimensional output of a DNSM, but train in the same way
2 participants
@matsen @willdumm