#!/usr/bin/env bash
# Chained after the 1.7B rung: re-run the 0.6B carrier on the SAME unwrapped corpus.
#
# The 1.7B run moved two variables at once -- carrier size AND corpus typography --
# because the unwrap could not wait if every further rung was to avoid inheriting the
# Gutenberg line breaks. That makes a 0.6B-vs-1.7B comparison descriptive rather than
# attributable, which is fine for "did sense come back" (a within-arm reading) and not
# fine for anything quantitative between rungs.
#
# This closes that hole for the price of ~36 minutes on an idle experimental box:
# 0.6B on the unwrapped corpus, seed 4919, everything else held. Then carrier size is
# the ONLY difference between this and h02-1p7b-1ep, and the sweep is single-variable
# again.
#
# ⚠ Gated on the 1.7B run having actually produced an adapter. If that run died, this
# must not quietly start and consume the box; a chain that fires on failure turns one
# lost run into two.
set -uo pipefail
PREV=/home/infra-ops/r49-runs/h02-1p7b-1ep
OUT=/home/infra-ops/r49-runs/h02-0p6b-1ep-unwrapped
LOG=$OUT/train.log
CHAINLOG=/home/infra-ops/r49-runs/chain-0p6b-unwrapped.log

exec >> "$CHAINLOG" 2>&1
echo "=== $(date -Is) chain armed, waiting on $PREV"
while [ -f "$PREV/run.pid" ] && kill -0 "$(cat "$PREV/run.pid")" 2>/dev/null; do sleep 60; done
echo "=== $(date -Is) 1.7B run finished"

if [ ! -f "$PREV/adapter/adapter_model.safetensors" ]; then
  echo "=== REFUSING to chain: $PREV produced no adapter -- the 1.7B run did not succeed"
  exit 1
fi
apps=$(nvidia-smi --query-compute-apps=pid --format=csv,noheader | tr -d '[:space:]')
if [ -n "$apps" ]; then
  echo "=== REFUSING to chain: GPU not clear"
  nvidia-smi --query-compute-apps=pid,process_name,used_memory --format=csv
  exit 1
fi

mkdir -p "$OUT"
echo "# launched $(date -Is) Qwen3-0.6B-Base, 1 epoch, seed 4919, UNWRAPPED corpus (single-variable partner to h02-1p7b-1ep)" > "$LOG"
setsid nohup /home/infra-ops/ml/.venv/bin/python /home/infra-ops/r49-prep/train_voice_lora.py \
  --corpus /home/infra-ops/r49-corpus-renamed-unwrapped \
  --base /home/infra-ops/carriers/Qwen3-0.6B-Base \
  --seed 4919 --epochs 1 --eval-steps 25 --save-steps 25 \
  --out "$OUT" >> "$LOG" 2>&1 < /dev/null &
echo $! > "$OUT/run.pid"
echo "=== $(date -Is) chained 0.6B launched pid $(cat "$OUT/run.pid") -> $LOG"