chore: snapshot in-progress question-gen work before preflight fixes

2026-07-16 04:12:21 -04:00
parent 11a5545f57
commit a4c429b247
39 changed files with 738 additions and 283 deletions
@@ -0,0 +1,95 @@
+#!/usr/bin/env bash
+# Action Recognition 训练 — 基于 SubPattern 靶向生成的 AR30 题
+#
+# 三阶段:
+#   Phase 0: baseline infer (AR30 题 + VME benchmark 作为 test)
+#   Phase 1: create seed (ar30-baseline)
+#   Phase 2: train (3 epochs, per_category)
+#
+# 用法:
+#   CUDA_VISIBLE_DEVICES=0 bash scripts/train_ar30.sh
+#   MODE=mock bash scripts/train_ar30.sh   # 跳过 Phase 0/1
+#
+# 与上次训练的区别:
+#   - 题目来源: generated-ar30（SubPattern 靶向）替代 generated-v2-360（OCR 污染）
+#   - seed 名: ar30-baseline（独立于旧的 v2ar-baseline）
+#   - workspace: workspaces/train-ar30
+
+set -euo pipefail
+
+cd "$(dirname "$0")/.."
+
+CUDA_VISIBLE_DEVICES="${CUDA_VISIBLE_DEVICES:-0}"
+export CUDA_VISIBLE_DEVICES
+
+export HF_HUB_OFFLINE=1
+export TRANSFORMERS_OFFLINE=1
+export PYTHONUNBUFFERED=1
+
+set -a
+source .env
+set +a
+
+PYTHON="$(conda run -n Video-Tree-TRM which python)"
+
+# ── Phase 0: Baseline infer（用 AR30 新题跑基线推理）──
+if [[ "${MODE:-}" != "mock" ]]; then
+    echo "=== Phase 0: Baseline infer (AR30 新题 30 题) ==="
+    "${PYTHON}" main.py \
+        --config config/train_ar30.yaml \
+        --workspace-dir workspaces/default \
+        --store-dir store \
+        --mode infer \
+        --concurrency 24 \
+        --max-steps 40 \
+        --skill-mode auto \
+        --n-samples 0 \
+        --questions "generated-ar30" \
+        --skills-version v1 \
+        --prompts-version v1 \
+        --run-id ar30_baseline \
+        --task-types "Action Recognition"
+fi
+
+# ── Phase 1: Create seed ──
+if [[ "${MODE:-}" != "mock" && ! -d "store/seeds/ar30-baseline" ]]; then
+    echo "=== Phase 1: Create seed ar30-baseline ==="
+    "${PYTHON}" -c "
+from pathlib import Path
+from app.harness.store import extract_run_db, init_seed
+import tempfile
+
+tmp = Path(tempfile.mkdtemp()) / 'baseline.db'
+extract_run_db(
+    Path('workspaces/default/harness.db'),
+    tmp,
+    'infer_ar30_baseline',
+)
+init_seed(
+    store_dir=Path('store'),
+    name='ar30-baseline',
+    skills_dir=Path('store/skills/v1'),
+    prompts_dir=Path('store/prompts/v1'),
+    baseline_db=tmp,
+    baseline_run_id='infer_ar30_baseline',
+    parent=None,
+    description='AR30 SubPattern 靶向题 baseline (skills/v1)',
+)
+tmp.unlink()
+print('Seed created: store/seeds/ar30-baseline/')
+"
+elif [[ -d "store/seeds/ar30-baseline" ]]; then
+    echo "=== Phase 1: Seed ar30-baseline 已存在，跳过 ==="
+fi
+
+# ── Phase 2: Train ──
+echo "=== Phase 2: Train (3 epochs, AR30) ==="
+"${PYTHON}" main.py \
+    --config config/train_ar30.yaml \
+    --fresh \
+    --seed ar30-baseline
+
+echo "=== 训练完成 ==="
+echo "结果查看:"
+echo "  cat workspaces/train-ar30/analyses/final_test_eval.json"
+echo "  sqlite3 workspaces/train-ar30/harness.db 'SELECT * FROM dual_metric'"