OLMo2 1B experiments #852
Closed
OLMo2 1B experiments #852
Conversation
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
Contributor
|
Dirk would probably have an opinion on this, we typically avoid releasing ablations and experiment setups because once we do it for one model, people start requesting checkpoints and data mixes for every other size, You did it for 1B, please do it for 7B, 13B, 32B..I ran into this issue with olmoe, I got a lot of requests for ablation-related artifacts, and it took significant effort to track everything down and upload it to R2. |
Contributor
Author
|
Lol okay, lemme make a clean version with ablation experiments purged |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
There are a few experimental config files and launch scripts that resulted in the official 1B release. I thought it'd be nice to push these in for completeness. Not urgent.
Most stuff in this PR are experiments for the 1B pretraining investigation.