wassname
fa24f4eb4b
- Drop gradient_checkpointing: at G=6 grad-accum forwards one 6-seq group at a time, so activation peak fits on 96GB without recompute; removes the ~1.3-1.5x backward recompute. enable_input_require_grads was a checkpointing-only trick. - Toggle use_cache=True around model.generate (False for the loss forwards). Cacheless decode was O(L^2); measured 2.17x faster with cache on the wrapped 4B. - Replace end-of-run torch.save(.pt) with save_ckpt(): trainable delta_S as safetensors tensors + rows/config as JSON metadata (str->str), written every 25 steps and at the end so an early kill keeps progress. Mirrors v_hack idiom. - Per-step TIMING log (gen / fwd_bwd / reward) to attribute wall-time. Diagnosed generation as ~93% of step cost (HF generate slow; full-rank reparam adds 1.5x). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
projected_grpo
SVD-basis gradient projection vs RL reward hacking. Tests whether projecting the training gradient orthogonal to an extracted hack-direction (in the SVD-of-W basis) reduces reward-hack rate in GRPO without tanking pass rate.
Built on Ariahw, Engels & Nanda's rl-rewardhacking LeetCode benchmark. Method differs from concurrent work (Wu & Tang 2026, "Advantage Modification") by intervening at the gradient level rather than the advantage level.
See docs/spec.md, docs/brainstorm/extracted_prefs.md, and docs/papers/.
Quick start
uv sync
just fast-dev-run # tiny-random model, ~1-2 min, real pipeline end-to-end
just smoke-vanilla # vanilla pathway smoke
just smoke-projected # projected pathway smoke
just download-model # warm Qwen3-4B cache (full preset peaks ~73GB on 96GB)
just queue-full # queue extract + 3-seed vanilla + 3-seed projected sweep
See RESEARCH_JOURNAL.md for session-by-session findings,
including the 2026-05-23 grader-bug discovery that invalidated all prior gt=0
measurements and the move from Qwen3.5-2B to Qwen3-4B (reference substrate).
Hypotheses (preregistered)
See spec.md. Headline: H1 — gradient projection in SVD basis against a v_hack extracted from ~60-80 contrastive pairs reduces reward hack rate by
=30pp absolute vs vanilla GRPO at matched LeetCode pass rate (±10pp).