#!/usr/bin/env bash
# BabyYarros — Qwen3-4B-BASE, 1 epoch, seed 4919. The comparison partner to the
# instruct arm: same corpus, same seed, same everything, CARRIER is the only variable.
#
# Why it exists: one arm is not a comparison. On the Brontë corpus Base won held-out
# loss (2.814 vs the instruct arm's 2.908) while instruct won instruction-following
# (on-beat 10/10 through the chat template, task-leak 0/18). That trade is the whole
# open question for Skaldsong, and it has to be re-measured per corpus rather than
# carried over -- the Yarros corpus is 12% larger and contemporary rather than 1840s.
#
# ⚠ Expect the loss minimum EARLY. The Brontë 4B-Base rung overfit inside one epoch
# and turned at step 75 of 159; its shipped adapter/ was NOT the best weights. Hence
# eval + save every 25 so the minimum is LOCATED, and arms get cut from the checkpoint.
#
# --allow-shared-gpu DELIBERATELY bypasses the GPU-clear guard, for the measured case
# where a second run fits and the operator has asked for concurrency. It is an explicit
# argument and not a default, because the guard's normal job -- stopping a chain from
# firing into a live run -- is the thing that keeps one lost run from becoming two.
set -euo pipefail
SHARED=0
[ "${1:-}" = "--allow-shared-gpu" ] && SHARED=1

OUT=/home/infra-ops/r49-runs/yarros-4b-base-1ep
LOG=$OUT/train.log
CORPUS=/home/infra-ops/yarros-corpus-renamed

if [ "$SHARED" = "0" ]; then
  apps=$(nvidia-smi --query-compute-apps=pid --format=csv,noheader | tr -d '[:space:]')
  [ -n "$apps" ] && { echo "REFUSING: GPU not clear (pass --allow-shared-gpu to override)" >&2; \
    nvidia-smi --query-compute-apps=pid,process_name,used_memory --format=csv >&2; exit 1; }
fi
[ -e "$LOG" ] && { echo "REFUSING: $LOG exists" >&2; exit 1; }

# ⚠ Same gate guard as the instruct arm. Training on ungated text is the one failure
# this pipeline exists to prevent, and a launcher that trusts a human to have
# remembered is not a guard.
python3 - "$CORPUS/leak_gate_report.json" <<'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, controls pos={c['positive_pass']} "
      f"neg={c['negative_pass']}, 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 $(date -Is) Qwen3-4B-Base, 1 epoch, seed 4919, shared_gpu=$SHARED" > "$LOG"
echo "# corpus $CORPUS sha $CSHA (leak gate PASSED)" >> "$LOG"
[ "$SHARED" = "1" ] && echo "# ⚠ CONCURRENT with another training job -- s/it in this log is NOT comparable to a solo run" >> "$LOG"
setsid nohup /home/infra-ops/ml/.venv/bin/python /home/infra-ops/r49-prep/train_voice_lora.py \
  --corpus "$CORPUS" \
  --base /home/infra-ops/carriers/Qwen3-4B-Base \
  --seed 4919 --epochs 1 --eval-steps 25 --save-steps 25 \
  --out "$OUT" >> "$LOG" 2>&1 < /dev/null &
echo $! > "$OUT/run.pid"
echo "launched pid $(cat "$OUT/run.pid") -> $LOG  (corpus sha $CSHA, shared_gpu=$SHARED)"