Skip to content

Sophiex/dev ssl/deep ssl#2113

Open
sophie-xhonneux wants to merge 27 commits intodevelopfrom
sophiex/dev-ssl/deep-ssl
Open

Sophiex/dev ssl/deep ssl#2113
sophie-xhonneux wants to merge 27 commits intodevelopfrom
sophiex/dev-ssl/deep-ssl

Conversation

@sophie-xhonneux
Copy link
Copy Markdown
Contributor

Description

Implement deep SSL, i.e. take intermediate encoder layers + context loss from V JEPA 2.1

Issue Number

Is this PR a draft? Mark it as draft.

Checklist before asking for review

  • I have performed a self-review of my code
  • My changes comply with basic sanity checks:
    • I have fixed formatting issues with ./scripts/actions.sh lint
    • I have run unit tests with ./scripts/actions.sh unit-test
    • I have documented my code and I have updated the docstrings.
    • I have added unit tests, if relevant
  • I have tried my changes with data and code:
    • I have run the integration tests with ./scripts/actions.sh integration-test
    • (bigger changes) I have run a full training and I have written in the comment the run_id(s): launch-slurm.py --time 60
    • (bigger changes and experiments) I have shared a hegdedoc in the github issue with all the configurations and runs for this experiments
  • I have informed and aligned with people impacted by my change:
    • for config changes: the MatterMost channels and/or a design doc
    • for changes of dependencies: the MatterMost software development channel

@sophie-xhonneux sophie-xhonneux self-assigned this Mar 26, 2026
@github-actions github-actions bot added data Anything related to the datasets used in the project eval anything related to the model evaluation pipeline labels Mar 26, 2026
@github-actions github-actions bot added infra Issues related to infrastructure model Related to model training or definition (not generic infra) labels Mar 26, 2026
We identified a bug whereby  context loss is only computed on the last
layer. This will be fixed in the next commits, but we need to save the
current state for reproducibility.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

data Anything related to the datasets used in the project eval anything related to the model evaluation pipeline infra Issues related to infrastructure model:pretrain model Related to model training or definition (not generic infra)

Projects

Status: No status

Development

Successfully merging this pull request may close these issues.

2 participants