#!/usr/bin/env bash
# R49 H02 — the instruct probe. Qwen3-4B (INSTRUCT, not -Base), 1 epoch, seed 4919.
#
# WHY, in the operator's words: "I think we need the instruct model trained -- if
# nothing else to see what our options are." Three arguments drove it and all three
# are about the REGIME rather than the output quality:
#
#   1. A completion carrier reaches for BRONTË's plot devices, not Skaldsong's. We
#      measured that: the gloom-override killed the animals on a prompt that asked
#      for a wonderful story, and the rename pool rewrote "Alice" into "Alexander
#      the Alexander". When the author owns the plot, importing hers is a conflict,
#      not a blemish.
#   2. Drift scales with generated length. In the ten-format bake-off the short
#      samples stayed nearest the beat and the 224-253 word ones wandered furthest.
#   3. ⭐ If a frontier model must judge every paragraph, the tiny model has no
#      purpose. Reliability has to be intrinsic, not bought back downstream.
#
# ⚠ THIS IS A PROBE, NOT THE PRODUCT PATH. It trains RAW CONTINUATION text into a
# model whose weights expect <|im_start|> framing, which can degrade the template
# behaviour — that is exactly the risk being measured, and the reason the chained
# test drives it through the chat template afterwards. The product path builds an
# instruction-pair corpus; that is a separate and larger piece of work, and it is
# only worth starting if instruction-following survives this.
#
# Everything else held from the 4B-Base rung so the CARRIER is the only variable:
# unwrapped corpus (sha 77f37057b2782e49), seed 4919, rank 32, lr 1e-4, seq 4096,
# batch 1 x accum 8, 1 epoch, eval+save every 25.
#
# ⚠ Expect the loss minimum EARLY. 4B-Base turned at ~step 75 of 159, and an
# instruct model already fluent in English should saturate at least as fast.
set -euo pipefail
OUT=/home/infra-ops/r49-runs/h02-4b-instruct-1ep
LOG=$OUT/train.log
apps=$(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: $LOG exists" >&2; exit 1; }
mkdir -p "$OUT"
echo "# launched $(date -Is) Qwen3-4B INSTRUCT, 1 epoch, seed 4919, unwrapped corpus" > "$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/Qwen3-4B-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"