mlcommons / mlcommons/hpc

[cosmoflow] [logging] Weight decay and l2 regularization differs by a factor of 2

Open
#22 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Jupyter Notebook
Stars
51
Forks
24
PR merge metrics
No merged PRs in 30d

Description

Weight decay and l2 regularization differs by a factor of 2. (Refs)
I think the value of Weight Decay output in the following line should be "l2 * 2".

https://github.com/mlcommons/hpc/blob/b796e7aec0339b8a2d33e7af3c875ebe74f038aa/cosmoflow/models/cosmoflow.py#L52

Refs

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start at cosmoflow/models/cosmoflow.py#L52 and read how the weight decay and L2 values are defined and reported. Review the linked weight-decay references to establish the convention being used, then verify the corrected value against the surrounding implementation. Done means the reported relationship is consistent with that convention.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.