diff options
| author | Will DePue <williamd@openai.com> | 2026-03-18 16:32:14 -0700 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2026-03-18 16:32:14 -0700 |
| commit | 9f170d4c818840e417c69d9148eb63eedd916861 (patch) | |
| tree | 0ec3d87e765a23ac9594cc8b76c5a67ac38efdd5 | |
| parent | 825357724a36e54bb61dca99700b21b07aaa8c47 (diff) | |
Update README.md
| -rw-r--r-- | README.md | 2 |
1 files changed, 1 insertions, 1 deletions
@@ -144,7 +144,7 @@ There's no perfectly clear answer here and it's hard to draw a clean line around **What are the restrictions on evaluation?** -We won't accept submissions that take more than 10 minutes on 8xH100 to evaluate, but otherwise you're free to evaluate however. As with modded-nanogpt, we allow evaluation at any sequence length. And, obviously, you aren't allowed to access any training data during evaluation, unless you pay for those bits in the <16MB limit. We encourage competitors to push the bounds of evaluation methods as aggressively as with training methods. +We won't accept submissions that take more than 10 minutes on 8xH100 to evaluate (Note: This limit is in addition to the 10 minutes of training time allowed!), but otherwise you're free to evaluate however. As with modded-nanogpt, we allow evaluation at any sequence length. And, obviously, you aren't allowed to access any training data during evaluation, unless you pay for those bits in the <16MB limit. We encourage competitors to push the bounds of evaluation methods as aggressively as with training methods. ## Submission Process |
