WIP Record: SP8192 + CaseOps + Depth Curriculum + FreqGPTQ + PPM adaptive-λ mixture — val_bpb 0.90687688 (1-seed)#1833
Draft
pragnyanramtha wants to merge 17 commits intoopenai:mainfrom
Draft
Conversation
Agent-Logs-Url: https://github.com/pragnyanramtha/parameter-golf/sessions/bf90bb43-1ad3-42a4-980f-612ebe31b0b0 Co-authored-by: pragnyanramtha <196208154+pragnyanramtha@users.noreply.github.com>
Agent-Logs-Url: https://github.com/pragnyanramtha/parameter-golf/sessions/bf90bb43-1ad3-42a4-980f-612ebe31b0b0 Co-authored-by: pragnyanramtha <196208154+pragnyanramtha@users.noreply.github.com>
…d-freq-gptq-support # Conflicts: # records/track_10min_16mb/record3/train_gpt.py Co-authored-by: pragnyanramtha <196208154+pragnyanramtha@users.noreply.github.com>
Copilot/add freq gptq support
…-golf into record/attempt3
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Builds on romeerp's #1756 depth curriculum stack. Adds two techniques:
FreqGPTQ — upweights top-100 most frequent calibration tokens by 2×
during Hessian collection, improving int6 quantization quality on
high-frequency vocabulary items.
PPM-D adaptive-λ mixture (from OE-GOD Record: SP4096 + byte-level PPM adaptive-λ mixture — val_bpb 1.01925 (3-seed) #1785) — byte-level PPM order-5
predictor mixed with NN log-probs at eval time using adaptive gate:
λ=0.05 when PPM confidence >0.9, λ=0.9 otherwise. Zero artifact cost.
Results (1-seed, 8×H100 SXM)
Status
Single seed screening run. Two known issues being fixed:
aggressive int8 passthrough quantization)
Full 3-seed compliant submission pending fixes.
Base
Fork of romeerp #1756 (CaseOps + depth curriculum 1→3→4)`