3 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
wassnameandClaudypoo	fbacefd433	fix: bf16/cuda path (7 device+dtype bugs) + GPU-bf16 smoke ... The fp32+CPU smoke never walked the fast/full bf16+cuda path, so the whole device/dtype class was invisible to the only gate. The GPU path had in fact never run end-to-end. Seven bugs, each masked by fp32+CPU: - svd cache key: numpy has no bf16 -> hash via .view(uint8) - svd save: safetensors needs contiguous cpu tensors - svd cache-hit: load_file returns cpu -> .to(W) for device+dtype - delta_S/delta_S_hack created on cpu -> device=lin.weight.device (else the forward hook mixes cpu/cuda) - V_hack is fp32 (svd) but grads are bf16 -> cast to delta_S's space - completion_nll fed cpu ids to the cuda model in extraction - extraction orientation vote D@V.T mixed bf16 D with fp32 V Smoke is now tiny-random on GPU in bf16 (same device+dtype as fast/full), so this class stays caught. All arms (none/erase/route) and extraction paths (miss/hit/refresh) green: cin_t~0.31-0.41, cout~0 (one_sided identity). Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>	2026-06-01 03:21:08 +00:00
wassname	25ad306763	readme	2026-06-01 00:19:30 +00:00
wassnameandClaudypoo	b0d1bcd3d5	Rebuild src/ from pseudocode: SVD-basis gradient projection vs GRPO reward hacking ... Expand docs/pseudocode/01..07 into a slim, fail-fast src/projected_grpo/ that passes `just smoke`. Code mirrors the pseudocode (δS/Σ/V names, relu-before-agg cin/cout, Dr.GRPO unbiased loss). Did not read the original src. 7 modules (~880 LOC): - rewards.py grader + 4 loophole modes + hack x mode diagonal self-check (R1) - problems.py tiny LeetCode substrate + contrastive pairs (R5) - antipasto.py SVD adapter, identity at δS=0 (R2) - proj.py erase/route/measure_only projection (R3) - extract_vhack_grad.py per-module SVD of paired grad diffs, noise floor (R5) - train.py mixed student+teacher GRPO loop, presets smoke/fast/full (R4) - build_pool.py self-contained frozen teacher-pool fixture `just smoke-all` PASS (exit 0): erase/none/route trio, grader diagonal clean, v_hack cache miss->hit, ckpt every-25. Fresh-eyes review: 6/6 mechanics faithful. Simplifications: merged loopholes+verify_rewards->rewards, pairs->problems; flat Config + `train.py {preset} [--overrides]` CLI; justfile 384->71 lines; trimmed results table; token-efficient train logging (config anchor, SHOULD at loop site, sparse tqdm postfix, BLUF tail with cue + direction-arrow table). Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>	2026-05-31 14:06:42 +00:00