Skip to content

Conversation

metric-space
Copy link
Contributor

@metric-space metric-space commented Jul 30, 2024

Fixes

  1. uncaught dataset loader bug that pops up because padding wasn't set correctly

Improves

  1. Use of transpose law to simplify expression
  2. Removes unnecessary complexity and unifies averaging for every weight matrix as opposed to the previous conditional

Testing

Has been tested multiple times with the original (smoke) testing script and alignment has been gauged via cosine angles and frob norms

@metric-space metric-space marked this pull request as draft August 8, 2024 15:49
@metric-space metric-space removed the request for review from thomasgauthier August 26, 2024 04:33
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant