Add masked-window FM processor#412
Draft
sgreenbury wants to merge 5 commits into
Draft
Conversation
Add a flow-matching processor variant that masks temporal windows so RB experiments can train with the masked-window objective.
Add the first Rayleigh-Benard masked-window FM submit script so the new processor can be launched with the comparison workflow.
Revise the masked-window submit script with the final RB launch settings needed for the comparison run.
Clean up lint failures in the masked-window FM branch without changing the training behavior.
Only auto-fill encoder input channels when that key exists. This preserves configs without in_channels while keeping RB auto setup.
1 task
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
input-plus-output trajectory window while clamping sampled context states.
including setup-time resolution of automatic input/output/channel sizes.
cached LOLA latents and the LOLA-style epoch/step budget.
and input-channel validation.
Testing