Add SP4096 qk45 budget reproduction candidate#2161
Open
adiprathapa wants to merge 1 commit into
Open
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Adds a non-record SP4096 budget reproduction/iteration based on Kevin Clark's 2026-04-01 SP4096 record. The run uses a 1xH100 RunPod budget setup with 86 SP4096 train shards and a 3600 second cap.
Best valid result:
val_bpb:1.10743376sliding-window eval15,987,19542QK_GAIN_INIT=4.5Notes
This is submitted as non-record because it does not meet the official 10 minute / 8xH100 compute constraint. The folder includes run logs and notes, but not the ignored
.ptzartifacts.Validation
python3 -m py_compile records/track_non_record_16mb/2026-05-07_sp4096_budget_repro/train_gpt.pypython3 -m json.tool records/track_non_record_16mb/2026-05-07_sp4096_budget_repro/submission.jsonrunpod_results/