Repository navigation
docs(WO64): r8 stage-2 final verdict — negative at both checkpoints - #348
Merged
Merged
Conversation
…kills the overfit hypothesis
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The oepoch-0 control scores DER-CE 6.96 vs oepoch-1's 7.13 — the same within noise, so the continuation did not overfit; it simply never inherited the teacher's quality. The oracle-relabeled targets are the bottleneck (the Thai-arm lesson repeated: low train loss is not evidence when the targets are). R8 ships nothing; its infrastructure is the salvage. B3's SOTA path stays on the published v1-lineage numbers + VRR.