Mosh Levy
moshlevy.bsky.social
Mosh Levy
@moshlevy.bsky.social
phd student @biunlp.
studying ai robustness and behaviors.
Anyone know how to map an Olmo checkpoint to a specific subset of its training data?
How does one figure out exactly which samples were seen in training for a given OLMo checkpoint? Where is that information shared or stored?
Also, there used to be a csv of checkpoints in the OLMo repo, but it's gone (guessing since OLMo 2)...
Help will be appreciated
December 15, 2024 at 2:50 PM
Reposted by Mosh Levy
Screenshot 1 from skeptical thread:
December 6, 2024 at 6:38 PM
Reposted by Mosh Levy
The good reviewer party™, a party at conferences for reviewers whose ACs said they did a great job. ML operates on FOMO so I think it'd work
November 24, 2024 at 8:09 PM