#!/usr/bin/env bash
# BabyYarros — Qwen3-4B INSTRUCT, 1 epoch, seed 4919, on the gated renamed corpus.
#
# Carrier is the instruct model on the operator's direction ("train the instruct on
# the yarros corpus -- babyyarros") and because the R49 instruct probe answered the
# question it was run to answer: voice and instruction-following COEXIST. On the
# Brontë corpus the instruct arm held curly quotes 16/18 -- identical to 4B-Base --
# took zero task-leak in 18 samples, and stayed on-beat 10/10 through the chat
# template, at a held-out 2.908 against Base's 2.814. The cost was length
# discipline (in-band 10/10 -> 6/10), not voice.
#
# ⚠ This still trains RAW CONTINUATION text into a model whose weights expect
# <|im_start|> framing. That is the known risk and it is the same one the Brontë
# probe measured; the product path (instruction-pair corpus, Skaldsong Option C)
# is separate and larger work.
#
# Everything else is held from the Brontë instruct arm so the CORPUS is the only
# variable: seed 4919, rank 32, lr 1e-4, seq 4096, batch 1 x accum 8, 1 epoch,
# eval + save every 25 so the loss minimum is LOCATED rather than assumed -- the
# 4B rung overfit inside one epoch and turned at step 75 of 159, and its shipped
# adapter/ was NOT the best weights.
#
# CORPUS PROVENANCE: 6 copies of 208 chapters, all five works, renamed under ONE
# corpus-wide map per copy. Leak gate PASSED -- 0 of 325 source entities and 0 of
# 91 audited phrases survive in any of the 30 copy files, both controls passing,
# sensitivity floor 3 occurrences for a name and 5 for a phrase.
set -euo pipefail
OUT=/home/infra-ops/r49-runs/yarros-4b-instruct-1ep
LOG=$OUT/train.log
CORPUS=/home/infra-ops/yarros-corpus-renamed

apps=$(nvidia-smi --query-compute-apps=pid --format=csv,noheader | tr -d '[:space:]')
[ -n "$apps" ] && { echo "REFUSING: GPU not clear" >&2; nvidia-smi --query-compute-apps=pid,process_name,used_memory --format=csv >&2; exit 1; }
[ -e "$LOG" ] && { echo "REFUSING: $LOG exists" >&2; exit 1; }

# ⚠ Refuse to train on a corpus whose gate has not passed. Training on ungated
# text is the one failure this whole pipeline exists to prevent, and a launcher
# that trusts a human to have remembered is not a guard.
GATE=$CORPUS/leak_gate_report.json
python3 - "$GATE" <<'PY'
import json, sys
r = json.load(open(sys.argv[1]))
c = r["controls"]
bad = (not c["positive_pass"] or not c["negative_pass"]
       or r["surviving_renameable"] or r["surviving_sub_threshold"]
       or r.get("surviving_phrases"))
print(f"  gate report: {r['renameable_total']} surfaces, "
      f"controls pos={c['positive_pass']} neg={c['negative_pass']}, "
      f"surviving {len(r['surviving_renameable'])} entities / "
      f"{len(r.get('surviving_phrases', {}))} phrases")
sys.exit(1 if bad else 0)
PY

mkdir -p "$OUT"
CSHA=$(cat "$CORPUS"/copies/*.jsonl | sha256sum | cut -c1-16)
echo "# launched $(date -Is) Qwen3-4B INSTRUCT, 1 epoch, seed 4919" > "$LOG"
echo "# corpus $CORPUS sha $CSHA (leak gate PASSED)" >> "$LOG"
setsid nohup /home/infra-ops/ml/.venv/bin/python /home/infra-ops/r49-prep/train_voice_lora.py \
  --corpus "$CORPUS" \
  --base /home/infra-ops/carriers/Qwen3-4B-Instruct \
  --seed 4919 --epochs 1 --eval-steps 25 --save-steps 25 \
  --out "$OUT" >> "$LOG" 2>&1 < /dev/null &
echo $! > "$OUT/run.pid"
echo "launched pid $(cat "$OUT/run.pid") -> $LOG  (corpus sha $CSHA)"