Add strong-submission eval pipeline and ablation tooling#153
Open
RogueTex wants to merge 1 commit intoopenai:mainfrom
Open
Add strong-submission eval pipeline and ablation tooling#153RogueTex wants to merge 1 commit intoopenai:mainfrom
RogueTex wants to merge 1 commit intoopenai:mainfrom
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
FINAL_EVAL_MODE=standard|sliding|tttEVAL_SEQ_LEN,EVAL_STRIDE,EVAL_BATCH_SEQS) with compiledforward_logitsMUON_WEIGHT_DECAYINT8_ALWAYS_KEEP_FLOAT_NAME_PATTERNS(default keepstok_emb.weightin fp16)experiments/parameter_golf/Why
This makes it possible to run controlled ablations and push for stronger 10min/16MB submissions by combining training-side robustness and evaluation-time improvements.
Validation
python3 -m py_compile train_gpt.pybash -n experiments/parameter_golf/run_ablation.shbash -n experiments/parameter_golf/run_top3.shpython3 experiments/parameter_golf/summarize_runs.py --helpNotes
GPU training/eval sweeps were not run in this local environment (no CUDA tooling present).