Files
evil_MoE/src/projected_grpo/verify_vhack_heldout.py
T
2026-05-23 14:19:41 +08:00

135 lines
4.6 KiB
Python

"""Held-out v_hack validation (spec.md §B validation).
For each held-out pair, compute per-module gradient diff (g_hack - g_clean)
in delta_S basis, then cos-align with the trained v_hack[name].
Report:
- per-suffix median/mean cos_align
- fraction of modules with cos_align > 0 (SHOULD > 0.5)
- mean cos_align across modules (target > 0.2)
Run: uv run python -m projected_grpo.verify_vhack_heldout
"""
from __future__ import annotations
import sys
from collections import defaultdict
from dataclasses import dataclass
from pathlib import Path
import torch
import tyro
from loguru import logger
from tabulate import tabulate
from transformers import AutoModelForCausalLM, AutoTokenizer
from .antipasto import wrap_model_with_antipasto
from .extract_vhack_grad import completion_nll, resolve_dtype
from .pairs import PAIRS
from .train import load_v_hack
CACHE_ROOT = Path("svd_cache")
OUT_DIR = Path("out")
@dataclass
class Config:
model: str = "Qwen/Qwen3.5-0.8B"
dtype: str = "bf16" # must match extract_vhack_grad.py and train.py
v_hack_path: Path = OUT_DIR / "v_hack_smoke.pt"
out_path: Path = OUT_DIR / "vhack_heldout_cos.pt"
n_heldout: int = 5
def main(cfg: Config) -> int:
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
dtype = resolve_dtype(cfg.dtype)
logger.info(f"device={device} model={cfg.model} dtype={cfg.dtype}")
held = PAIRS[-cfg.n_heldout:]
logger.info(f"held-out pairs: {len(held)}")
tokenizer = AutoTokenizer.from_pretrained(cfg.model)
model = AutoModelForCausalLM.from_pretrained(
cfg.model, dtype=dtype, attn_implementation="sdpa"
).to(device)
model.eval()
wrappers = wrap_model_with_antipasto(
model, model_name=cfg.model, cache_root=CACHE_ROOT, svd_device=device,
)
v_hack = load_v_hack(cfg.v_hack_path, cfg.model, wrappers)
logger.info(f"loaded v_hack: {len(v_hack)} modules")
grads_hack: dict[str, list[torch.Tensor]] = defaultdict(list)
grads_clean: dict[str, list[torch.Tensor]] = defaultdict(list)
for pi, pair in enumerate(held):
for label, completion in (("hack", pair.hack), ("clean", pair.clean)):
model.zero_grad(set_to_none=True)
loss = completion_nll(model, tokenizer, pair.prompt, completion, device)
loss.backward()
bucket = grads_hack if label == "hack" else grads_clean
for name, info in wrappers.items():
bucket[name].append(info["delta_S"].grad.detach().float().cpu().clone())
logger.info(f" held pair {pi+1}/{len(held)} loss={loss.item():.3f}")
# per-module cos_align
cos_by_suffix: dict[str, list[float]] = defaultdict(list)
all_cos = []
rows_all = []
for name, v in v_hack.items():
gh = torch.stack(grads_hack[name]).mean(0)
gc = torch.stack(grads_clean[name]).mean(0)
diff = gh - gc
nrm = diff.norm()
if nrm < 1e-12:
cos = 0.0
else:
cos = ((diff / nrm) @ v).item()
suf = name.split(".")[-1]
cos_by_suffix[suf].append(cos)
all_cos.append(cos)
rows_all.append((name, cos))
agg_rows = []
for suf, vals in sorted(cos_by_suffix.items()):
t = torch.tensor(vals)
agg_rows.append({
"suffix": suf,
"n": len(vals),
"mean_cos": f"{t.mean():+.3f}",
"median_cos": f"{t.median():+.3f}",
"frac>0": f"{(t > 0).float().mean():.2f}",
"min": f"{t.min():+.3f}",
"max": f"{t.max():+.3f}",
})
print(tabulate(agg_rows, headers="keys", tablefmt="pipe"))
t_all = torch.tensor(all_cos)
frac_pos = (t_all > 0).float().mean().item()
mean_cos = t_all.mean().item()
median_cos = t_all.median().item()
logger.info(
f"OVERALL modules={len(all_cos)} frac>0={frac_pos:.3f} "
f"mean={mean_cos:+.3f} median={median_cos:+.3f} "
f"SHOULD: frac>0 > 0.50 and mean > 0.20. ELSE: extraction noise dominates signal."
)
# save for downstream plotting / sanity
torch.save({"model": cfg.model, "dtype": cfg.dtype, "cos_align": rows_all}, cfg.out_path)
gate_pass = frac_pos > 0.50
target_pass = mean_cos > 0.20
if not gate_pass:
logger.error(f"GATE FAIL: frac>0 = {frac_pos:.3f} <= 0.50")
return 1
if not target_pass:
logger.warning(f"TARGET MISS: mean_cos = {mean_cos:+.3f} <= 0.20 (gate passes but signal weak)")
else:
logger.info(f"TARGET PASS: mean_cos = {mean_cos:+.3f} > 0.20")
return 0
if __name__ == "__main__":
sys.exit(main(tyro.cli(Config)))