esh-pfi-infrastructure/scripts/mccarthy-corpus/eval-mccarthy.sh

#!/bin/bash
# lv-mccarthy v2 gate. Design is FROZEN in scripts/mccarthy-corpus/GATE-PREREG.md
# and was written before this script ever ran. Do not edit the arms, the fixture
# size or the seeds to chase a result -- re-run, do not re-tune.
#
# THREE ARMS. ckpt900 is the eval-loss minimum (2.38706, epoch 1.958). ckpt450
# (2.4063, epoch 0.980) is +0.0193 against a 0.00393 median neighbour jitter =
# 4.9x, i.e. NOT tied -- and that is the difference from the Hemingway gate, where
# the second arm was a coin-flip. It is here to test a stated prior (on Bronte the
# earlier epoch-1 checkpoint won on the axes that resolve) and to price the
# memorisation headroom an earlier checkpoint would buy on an IN-COPYRIGHT author.
# `base` is the negative control for memorisation and the voice baseline.
# adapter/ (epoch 3.0, +18.4x jitter) is NOT gated: the loss curve settles that one.
set -o pipefail
cd ~/lv-mccarthy || exit 1
PY=/home/infra-ops/ml/.venv/bin/python
RUN=~/r49-runs/mccarthy-4b-pairs-3ep
OUT=~/r49-runs/mccarthy-eval
BEATS=beats-mccarthy-60.json
SIDE=beats-mccarthy-60.sidecar.json
PROV=pairs/pairs-full.jsonl.provenance.json
SEEDS="1234 5678 9012 3456"
mkdir -p "$OUT"
log(){ echo "[eval $(date +%H:%M:%S)] $*"; }

# --system-from is MANDATORY and it is load-bearing for the VOICE axis here, not
# merely hygienic. The mccarthy register NAMES the punctuation (no quote marks,
# `dont`/`aint`/`wont`), so driving the base control with the same prompt hands the
# cheap char-bigram win to BOTH sides and the adapter earns no delta for it. See
# GATE-PREREG.md section 5. The harness's built-in SYS is Yarros's; using it would
# confound the adapter change with a prompt change AND hand the adapter the win.
[ -f "$PROV" ] || { log "MISSING $PROV"; exit 1; }

# The run must have trained under the same system prompt the eval drives. Asserted,
# not assumed -- the Hemingway script claimed this was "verified" in a comment, which
# is a claim no reader can check. Here it fails the run.
"$PY" - "$PROV" "$RUN/provenance.json" <<'PYCHK' || exit 1
import json, sys
pairs = json.load(open(sys.argv[1]))
run = json.load(open(sys.argv[2]))
ps = pairs.get("system_prompt") or (pairs.get("register") or {}).get("system_prompt")
rs = run.get("system_prompt")
if ps is None:
    print(f"== CANNOT VERIFY: no system_prompt in {sys.argv[1]}"); sys.exit(1)
if ps != rs:
    print("== REFUSING: the run trained under a DIFFERENT system prompt than the eval would drive.")
    print(f"   pairs provenance: {ps[:120]!r}")
    print(f"   run provenance  : {(rs or '')[:120]!r}")
    sys.exit(1)
print(f"  [PASS] run system_prompt == pairs system_prompt ({len(ps)} chars)")
PYCHK

# 60 beats, max-words 140: the mccarthy register asks for 90-140 and score_beats.py
# scores the in-band rate at 90-140. Building the fixture at the script's default 150
# would put reference passages outside the band the product asks for.
if [ ! -s "$BEATS" ]; then
  log "building fixture"
  "$PY" scripts/r49-corpus/build_beat_fixture.py \
    --pairs pairs/pairs-val.jsonl --out "$BEATS" --sidecar "$SIDE" \
    -n 60 --seed 4919 --min-words 90 --max-words 140 || exit 1
else
  log "fixture $BEATS already exists -- reusing"
fi

# AMENDMENT 3 adds ckpt300 (ep 0.652) and ckpt225 (ep 0.489). Same fixture, same seeds,
# same rule -- adding candidates does not move a bar. Arms with generations already on
# disk are skipped, so re-running this script only fills in the new ones.
for arm in base:NONE ckpt900:$RUN/checkpoints/checkpoint-900 ckpt450:$RUN/checkpoints/checkpoint-450 \
          ckpt300:$RUN/checkpoints/checkpoint-300 ckpt225:$RUN/checkpoints/checkpoint-225; do
  name=${arm%%:*}; path=${arm#*:}
  if [ "$name" != "base" ] && [ ! -d "$path" ]; then log "MISSING $path"; exit 1; fi
  if [ -s "$OUT/beats5.$name.jsonl" ]; then
    log "arm $name already has $(wc -l < "$OUT/beats5.$name.jsonl") generations -- skipping"
    continue
  fi
  log "arm $name"
  if [ "$name" = "base" ]; then
    "$PY" scripts/r49-corpus/gen_beats_chat_yarros.py \
      --base ~/carriers/Qwen3-4B-Instruct --beats "$BEATS" \
      --out "$OUT/beats5.$name.jsonl" --arm "$name" --seeds $SEEDS \
      --system-from "$PROV" || exit 1
  else
    "$PY" scripts/r49-corpus/gen_beats_chat_yarros.py \
      --base ~/carriers/Qwen3-4B-Instruct --adapter "$path" --beats "$BEATS" \
      --out "$OUT/beats5.$name.jsonl" --arm "$name" --seeds $SEEDS \
      --system-from "$PROV" || exit 1
  fi
  log "  $(wc -l < "$OUT/beats5.$name.jsonl") generations"
done

log "AXIS B -- MEMORISATION (corpus = the renamed copies the adapter trained on)"
# --corpus and --eval-dir are passed explicitly: the script's Yarros defaults would
# compare a McCarthy arm against the YARROS corpus and report a clean zero that
# means "different book", not "did not memorise".
"$PY" scripts/yarros-corpus/memorization_check.py \
  --eval-dir "$OUT" --corpus corpus-renamed/copies --glob 'beats5.*.jsonl' --strip 'beats5.' -n 8 \
  2>&1 | tee "$OUT/memorization.txt"

for cand in ckpt900 ckpt450 ckpt300 ckpt225; do
  log "AXIS C -- DAMAGE (ran-on / out-of-band), $cand vs base"
  "$PY" scripts/yarros-corpus/score_beats.py \
    --arm base="$OUT/beats5.base.jsonl" \
    --arm ckpt900="$OUT/beats5.ckpt900.jsonl" \
    --arm ckpt450="$OUT/beats5.ckpt450.jsonl" \
    --arm ckpt300="$OUT/beats5.ckpt300.jsonl" \
    --arm ckpt225="$OUT/beats5.ckpt225.jsonl" \
    --baseline base --candidate "$cand" --metric-source raw \
    --out "$OUT/score.$cand.json" 2>&1 | tee "$OUT/score.$cand.txt"
done

log "AXIS A -- VOICE (delta_cb vs held-out McCarthy), + the pre-registered punct reads"
"$PY" scripts/mccarthy-corpus/voice-prep.py || exit 1
"$PY" scripts/r49-corpus/voice_distance.py corpus-renamed "$OUT" --author McCarthy \
  --punct-report --secondary-normalised \
  2>&1 | tee "$OUT/voice_distance.txt"

echo "rc=0" > ~/lv-mccarthy/.eval-complete
log "done"