feat(r49): D2/D3 complete and the H02 pilot is training on gx10
Entity resolution, deterministic rename augmentation, packing and the pilot trainer. Qwen3-0.6B-Base is training now: 507 steps, 11.2 s/it, ~1h35m. D2 -- gender resolution is TITLE-FIRST, and that is a change from F02's method rather than a port of it. F02 used pronoun proximity and recorded that it is structurally blind to the first-person narrator, whose name appears mainly in dialogue surrounded by other people's pronouns. Measured here, proximity called JANE MALE -- the narrator of Jane Eyre and the single worst entity to get wrong. Titles have no such blind spot: Miss Eyre, Mrs. Fairfax, Mr. Rochester, Madame Beck, M. Paul, and a 19th-century novel is saturated with them. Measured: 16 entities resolved, zero wrong, every ambiguous case landing on HELD -- shared family surnames like Helstone and Pelet genuinely belong to both a man and a woman and hold as they should. Held means ungendered, not unrenamed. A HELD entity is still renamed, from the gender-neutral surname pool, because the operator's Yarros directive was "rename all proper nouns" and holding a place leaks it -- Thornfield appears 100 times in Jane Eyre and is as author-specific as Riders Quadrant was. Substituting a neutral token makes no gender claim, so no gender claim can be wrong. D3 -- pool is French + English per the operator, weighted per work by setting: Brussels novels 60% French, Yorkshire novels 25%. Locales restricted to fr_FR/fr_BE/en_GB/en_IE; en_US and en_AU carry modern surnames that are wrong register for the 1840s. The pool is filtered against Brontë's own 75-letter alphabet, so French accents stay and Czech/Latvian marks do not. Two collision defects found by running the leak gate rather than trusting it: `Burns` and `Marie` were drawn as replacements while being Brontë characters -- F02's collision filter was built against Yarros and does not carry -- and then `Pierre-Yves` passed a whole-string filter while `Pierre` (Mademoiselle St. Pierre) is a Villette character. The filter now compares by COMPONENT. Final gate: 0 of 203 source entities survive in any of 24 copy-files. Trainer records what the run RESOLVED to rather than what it requested -- attention implementation, dtype, device, corpus sha and harness cleanliness are read back off the live objects. transformers 5.x has dropped warmup_ratio, caught by reading the signature after the first launch failed on it; the 3% warmup is computed into warmup_steps instead.
This commit is contained in:
@@ -0,0 +1,197 @@
|
||||
"""R49 Stage D2 (final) + D3 — entity resolution and deterministic rename augmentation.
|
||||
|
||||
D2's gender resolution is TITLE-FIRST, and that is the change from F02's method.
|
||||
F02 used pronoun proximity and recorded that it is structurally blind to the
|
||||
first-person narrator, whose name appears mainly in dialogue surrounded by other
|
||||
people's pronouns. Measured here on Bronte, proximity called **Jane male** -- the
|
||||
narrator of Jane Eyre, and the single worst entity to get wrong.
|
||||
|
||||
Titles do not have that blind spot. `Miss Eyre`, `Mrs. Fairfax`, `Mr. Rochester`,
|
||||
`Madame Beck`, `M. Paul` are unambiguous and a 19th-century novel is saturated
|
||||
with them. Measured: 16 entities resolved, **zero wrong**, with every ambiguous
|
||||
case landing on HELD rather than on a guess -- shared family surnames like
|
||||
Helstone and Pelet, which genuinely belong to both a man and a woman, hold as
|
||||
they should.
|
||||
|
||||
Held is cheap; wrong is poison. **A HELD entity is simply not renamed.** An
|
||||
un-renamed name costs a little augmentation; a mis-gendered one scrambles pronoun
|
||||
agreement through every copy and nothing downstream would catch it.
|
||||
|
||||
Pool is French + English (operator, 2026-09-10), weighted per work by setting:
|
||||
the Brussels novels draw more French, the Yorkshire novels more English. Locales
|
||||
are restricted to fr_FR/fr_BE/en_GB/en_IE -- en_US and en_AU carry modern
|
||||
surnames that are wrong register for the 1840s before any diacritic question.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
import argparse, collections, json, random, re, sys, unicodedata
|
||||
from pathlib import Path
|
||||
|
||||
TOKEN = re.compile(r"[A-Za-zÀ-ÿŒœÆæ][A-Za-zà-ÿœæ\-]*")
|
||||
MALE_T = r"(?:Mr|Sir|Master|Monsieur|M|Lord|Captain|Colonel|Major|Doctor|Dr|Reverend|King|Prince|Duke|Squire)"
|
||||
FEM_T = r"(?:Mrs|Miss|Madame|Mme|Mademoiselle|Mlle|Lady|Madam|Queen|Princess|Duchess)"
|
||||
|
||||
FRENCH_LOCALES = ["fr_FR", "fr_BE"]
|
||||
ENGLISH_LOCALES = ["en_GB", "en_IE"]
|
||||
#: Brussels novels lean French, Yorkshire novels lean English. Register, not
|
||||
#: orthography -- a Yorkshire mill town full of Parisian surnames reads wrong.
|
||||
FRENCH_SHARE = {"villette": 0.60, "the-professor": 0.60, "jane-eyre": 0.25, "shirley": 0.25}
|
||||
|
||||
|
||||
def title_gender(text: str) -> dict[str, str]:
|
||||
mt = collections.Counter(m.group(1).lower() for m in
|
||||
re.finditer(MALE_T + r"\.?\s+([A-ZÀ-Þ][a-zà-ÿœæ\-]+)", text))
|
||||
ft = collections.Counter(m.group(1).lower() for m in
|
||||
re.finditer(FEM_T + r"\.?\s+([A-ZÀ-Þ][a-zà-ÿœæ\-]+)", text))
|
||||
out = {}
|
||||
for k in set(mt) | set(ft):
|
||||
M, F = mt[k], ft[k]
|
||||
if M >= 3 and M >= 3 * max(F, 1):
|
||||
out[k] = "m"
|
||||
elif F >= 3 and F >= 3 * max(M, 1):
|
||||
out[k] = "f"
|
||||
return out
|
||||
|
||||
|
||||
def build_pool(dict_path: Path, alphabet: set[str]) -> dict:
|
||||
d = json.loads(dict_path.read_text())
|
||||
pool = {}
|
||||
for label, locales in (("fr", FRENCH_LOCALES), ("en", ENGLISH_LOCALES)):
|
||||
m, f, s = set(), set(), set()
|
||||
for loc in locales:
|
||||
v = d["by_locale"].get(loc, {})
|
||||
m |= set(v.get("male", []))
|
||||
f |= set(v.get("female", []))
|
||||
for k in ("surnames_neutral", "surnames_male", "surnames_female"):
|
||||
s |= set(v.get(k, []))
|
||||
# ⚠ F02's subset rule, applied with Bronte's OWN alphabet rather than a
|
||||
# global ASCII fold: French accents are IN because she writes French
|
||||
# constantly; Czech/Latvian/Slovak marks are OUT because they never appear.
|
||||
keep = lambda n: n and n[:1].isupper() and all((not c.isalpha()) or c in alphabet for c in n)
|
||||
pool[label] = {"male": sorted(filter(keep, m)),
|
||||
"female": sorted(filter(keep, f)),
|
||||
"surname": sorted(filter(keep, s))}
|
||||
return pool
|
||||
|
||||
|
||||
def main() -> int:
|
||||
ap = argparse.ArgumentParser()
|
||||
ap.add_argument("corpus")
|
||||
ap.add_argument("--entities", required=True)
|
||||
ap.add_argument("--dictionary", required=True)
|
||||
ap.add_argument("--out", required=True)
|
||||
ap.add_argument("--copies", type=int, default=6)
|
||||
ap.add_argument("--seed", type=int, default=4919)
|
||||
ap.add_argument("--holdout-chapter", type=int, default=10)
|
||||
a = ap.parse_args()
|
||||
|
||||
corpus = Path(a.corpus)
|
||||
man = json.loads((corpus / "manifest.json").read_text())
|
||||
alphabet = set(json.loads((corpus / "corpus_alphabet.json").read_text())["letters"])
|
||||
ents_all = json.loads(Path(a.entities).read_text())
|
||||
pool = build_pool(Path(a.dictionary), alphabet)
|
||||
# ⚠ Collision filter, against THIS corpus. F02 dropped 35 names for colliding
|
||||
# with the Yarros source so a rename could never map one of the author's
|
||||
# entities onto another; that filter is corpus-specific and does not carry.
|
||||
# Measured here before adding it: `Burns` and `Marie` were drawn as
|
||||
# replacements and are themselves Bronte entities, which reads as a leak in
|
||||
# the gate and is worse than it looks -- it silently merges two characters.
|
||||
source_names = {e["surface"] for w in ents_all.values() for e in w["entities"].values()}
|
||||
source_names |= {n.split()[0] for n in source_names if " " in n}
|
||||
dropped = 0
|
||||
for lang in pool:
|
||||
for bucket in pool[lang]:
|
||||
before = len(pool[lang][bucket])
|
||||
# ⚠ By COMPONENT, not by whole string. Measured: the pool drew the
|
||||
# compound `Pierre-Yves` while `Pierre` (Mademoiselle St. Pierre) is a
|
||||
# Villette character, so a whole-string comparison passed it and the
|
||||
# leak gate then matched the component. The original was correctly
|
||||
# renamed -- it is not a leak -- but a replacement sharing a component
|
||||
# with a source character invites exactly the conflation the rename
|
||||
# exists to prevent.
|
||||
pool[lang][bucket] = [
|
||||
n for n in pool[lang][bucket]
|
||||
if n not in source_names
|
||||
and not (set(re.split(r"[-\s’']", n)) & source_names)]
|
||||
dropped += before - len(pool[lang][bucket])
|
||||
print(f" collision filter: dropped {dropped} pool names that are Bronte entities")
|
||||
print(f" pool (alphabet-filtered): "
|
||||
f"fr {len(pool['fr']['male'])}m/{len(pool['fr']['female'])}f/{len(pool['fr']['surname'])}s "
|
||||
f"en {len(pool['en']['male'])}m/{len(pool['en']['female'])}f/{len(pool['en']['surname'])}s")
|
||||
|
||||
out = Path(a.out); (out / "copies").mkdir(parents=True, exist_ok=True)
|
||||
stats = {"copies": a.copies, "seed": a.seed, "works": {}, "renamed": 0, "held": 0}
|
||||
|
||||
works = {}
|
||||
for w in man["works"]:
|
||||
rows = [json.loads(l) for l in (corpus / w["path"]).read_text(encoding="utf-8").splitlines()]
|
||||
works[w["slug"]] = rows
|
||||
|
||||
# ---- D2 final: decide, per work, which entities are renameable ----------
|
||||
plans = {}
|
||||
for slug, rows in works.items():
|
||||
text = "\n\n".join(r["text"] for r in rows)
|
||||
tg = title_gender(text)
|
||||
ents = ents_all[slug]["entities"]
|
||||
titled = set(tg)
|
||||
renameable, held = {}, []
|
||||
for key, e in ents.items():
|
||||
if "’" in key or "'" in key or e["cap"] < 8:
|
||||
continue # possessives/contractions are not entities
|
||||
g = tg.get(key)
|
||||
if g:
|
||||
renameable[key] = {"surface": e["surface"], "kind": "given", "gender": g}
|
||||
else:
|
||||
# ⚠ Everything else is STILL renamed -- from the gender-NEUTRAL
|
||||
# surname/place pool. The operator's Yarros directive was "rename
|
||||
# all proper nouns", and holding a place leaks it: `Thornfield`
|
||||
# appears 100 times in Jane Eyre and is as author-specific as
|
||||
# `Riders Quadrant` was. Substituting a neutral token makes NO
|
||||
# gender claim, so no gender claim can be wrong -- the prose keeps
|
||||
# whatever pronoun it already had. Held-means-ungendered, not
|
||||
# held-means-unrenamed.
|
||||
renameable[key] = {"surface": e["surface"], "kind": "surname", "gender": None}
|
||||
held.append(key)
|
||||
plans[slug] = renameable
|
||||
stats["works"][slug] = {"renamed": len(renameable), "gendered": len(renameable)-len(held),
|
||||
"neutral": len(held)}
|
||||
stats["renamed"] += len(renameable); stats["held"] += len(held)
|
||||
print(f" {slug:<14} renamed {len(renameable):>3} ({len(renameable)-len(held)} gendered, {len(held)} neutral)")
|
||||
|
||||
# ---- D3: N seeded copies, one consistent map per copy -------------------
|
||||
emitted = 0
|
||||
for c in range(a.copies):
|
||||
rng = random.Random(a.seed + c * 1000)
|
||||
for slug, rows in works.items():
|
||||
fr_share = FRENCH_SHARE[slug]
|
||||
used = set()
|
||||
|
||||
def draw(kind: str, gender: str | None) -> str:
|
||||
lang = "fr" if rng.random() < fr_share else "en"
|
||||
bucket = {"m": "male", "f": "female"}.get(gender or "", "surname")
|
||||
for _ in range(200):
|
||||
n = rng.choice(pool[lang][bucket])
|
||||
if n not in used:
|
||||
used.add(n); return n
|
||||
return rng.choice(pool[lang][bucket])
|
||||
|
||||
mapping = {k: draw(v["kind"], v["gender"]) for k, v in plans[slug].items()}
|
||||
pat = re.compile(r"\b(" + "|".join(sorted((re.escape(v["surface"]) for v in plans[slug].values()),
|
||||
key=len, reverse=True)) + r")\b")
|
||||
surf2key = {v["surface"]: k for k, v in plans[slug].items()}
|
||||
path = out / "copies" / f"{slug}.copy{c}.jsonl"
|
||||
with path.open("w", encoding="utf-8") as fh:
|
||||
for r in rows:
|
||||
txt = pat.sub(lambda m: mapping[surf2key[m.group(1)]], r["text"])
|
||||
split = "val" if r["chapter"] == a.holdout_chapter else "train"
|
||||
fh.write(json.dumps({"work": slug, "copy": c, "chapter": r["chapter"],
|
||||
"split": split, "text": txt}, ensure_ascii=False) + "\n")
|
||||
emitted += 1
|
||||
print(f" copy {c}: written")
|
||||
|
||||
(out / "rename_stats.json").write_text(json.dumps(stats, ensure_ascii=False, indent=2))
|
||||
print(f"\n {emitted:,} chapter-records across {a.copies} copies -> {out}")
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
Reference in New Issue
Block a user