Support: independent PR2014 prefix-2400 reproduction, seed 42 val_bpb 1.05804#2078
Open
hi-aduek wants to merge 1 commit into
Open
Support: independent PR2014 prefix-2400 reproduction, seed 42 val_bpb 1.05804#2078hi-aduek wants to merge 1 commit into
hi-aduek wants to merge 1 commit into
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Independent seed-42 reproduction/support package for PR #2014.
This uses the PR #2014 SP8192 CaseOps progressive-3k stack, then reruns the saved quantized artifact with
PHASED_TTT_PREFIX_DOCS=2400to keep the validation-data TTT pass under the 600s eval cap on this 8xH100 SXM run.Result
This is intended as support evidence for PR #2014, not as a separate three-seed architecture claim.
Files
Adds one record folder:
records/track_10min_16mb/2026-04-30_SP8192_CaseOps_Progressive3k_Prefix2400_Repro_1.0580Includes README, submission.json, train/eval logs, train_gpt.py, CaseOps prep files, requirements, and tokenizer.