Non-record RTX4060Ti 11L LeakyTTT 24h local (1.1443 BPB)#1244
Open
monkeyKingProgrammer wants to merge 1 commit intoopenai:mainfrom
Open
Non-record RTX4060Ti 11L LeakyTTT 24h local (1.1443 BPB)#1244monkeyKingProgrammer wants to merge 1 commit intoopenai:mainfrom
monkeyKingProgrammer wants to merge 1 commit intoopenai:mainfrom
Conversation
monkeyKingProgrammer
changed the title
monkeyKingProgrammer
changed the title
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
A non-record unlimited-compute 16MB submission:
records/track_non_record_16mb/2026-04-02_11L_24h_Local4060Ti_LeakyTTT/This run was trained locally on
1x RTX 4060 Ti 16GBfor a24hwallclock cap, so it is not intended for the 10-minute8xH100main leaderboard.Final score:
legal_ttt_exact val_bpb: 1.14430187legal_ttt_exact val_loss: 1.93210066Artifact:
bytes_total: 15,702,576bytes_model_int6_lzma: 15,605,300bytes_code: 97,276This reuses the same 11-layer LeakyReLU^2 + Parallel Muon + XSA4 + Partial RoPE + LN scale + EMA + legal score-first TTT stack as the earlier 16-hour local run, but extends timed training to 24 hours at fixed
2048sequence length.