Thanks !

#1
by cdtmc - opened

This is very cool to open-source your full run - thank you!
Seems like you have +4.3 over the arcprize release after the same amount of steps. Looks potentially like single node training is better than multi-node.
I had some immediate thoughts for your consideration:

  1. Have you considered training run only using "concept" and "train" split and then try post-train techniques on "evaluation" split?
  2. Have you considered training run replacing "concept" with "arc-gen-100k"
  3. If you do manage to crack a post-train technique I think it would be interesting seeing a progressive train "arc-gen-100k", then "train" "evaluation" from arc2025 and finally submission on "test"

Any more open sourcing would be greatly appreciated

Ah ok, just seeing this now, sorry for that. Check https://trelis.com/arc-agi-2/ for a full report!

  1. Sounds reasonable. I didn't specifically try that but you can see some similar ablations in the report.
  2. I didn't and I'm not familiar with that dataset
  3. I'm not quite sure what you mean by "progressive train"

Sign up or log in to comment