zhangsiyuan
766b4811be
- code/src/data/: data_generator, dataset, llm_judge, __init__ (multi-turn LLM dialogue generator, JSONL loader, LLM auto-annotator) - code/scripts/: generate_siliconflow.py (SiliconFlow async generator, 701 lines) run_detector.sh / run_intervention.sh / run_full_pipeline.sh (launch scripts) - code/configs/intervention_config.yaml: add reward.w1-w5 reference block (NOTE: v5 reward.py uses hardcoded constants; these fields are reference-only) - .gitignore: fix data/ pattern to /data/ to avoid matching code/src/data/ Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
70 lines
2.9 KiB
Bash
70 lines
2.9 KiB
Bash
#!/bin/bash
|
|
# Full CompanionGuard-RL pipeline on 4x RTX 5090.
|
|
#
|
|
# Step 1: Generate data (calls LLM API, single process)
|
|
# Step 2: Annotate + split (calls LLM API, single process)
|
|
# Step 3: Train detector (4 GPU DDP, BF16)
|
|
# Step 4: Train intervention (4 GPU BC + 1 GPU PPO)
|
|
# Step 5: Evaluate (single GPU)
|
|
#
|
|
# Usage:
|
|
# export DASHSCOPE_API_KEY=your_key # for Qwen
|
|
# bash scripts/run_full_pipeline.sh
|
|
|
|
set -e
|
|
|
|
NUM_GPUS=4
|
|
echo "======================================================"
|
|
echo " CompanionGuard-RL Full Pipeline — 4x RTX 5090"
|
|
echo "======================================================"
|
|
|
|
# ── Step 1: Data generation ────────────────────────────────────────────
|
|
echo ""
|
|
echo "[1/5] Generating dataset..."
|
|
python scripts/generate_data.py --config configs/data_generation.yaml
|
|
|
|
# ── Step 2: LLM annotation + split ─────────────────────────────────────
|
|
echo ""
|
|
echo "[2/5] Annotating and splitting dataset..."
|
|
python scripts/annotate_data.py \
|
|
--input data/raw/generated.jsonl \
|
|
--output data/processed/annotated.jsonl \
|
|
--config configs/data_generation.yaml
|
|
|
|
# ── Step 3: Train detector ──────────────────────────────────────────────
|
|
echo ""
|
|
echo "[3/5] Training risk detector (4 GPU DDP, BF16)..."
|
|
accelerate launch \
|
|
--num_processes=${NUM_GPUS} \
|
|
--mixed_precision=bf16 \
|
|
--multi_gpu \
|
|
scripts/train_detector.py \
|
|
--config configs/detector_config.yaml
|
|
|
|
# ── Step 4: Train intervention policy ──────────────────────────────────
|
|
echo ""
|
|
echo "[4/5] Training intervention policy (BC: 4 GPU, PPO: 1 GPU)..."
|
|
accelerate launch \
|
|
--num_processes=${NUM_GPUS} \
|
|
--mixed_precision=bf16 \
|
|
--multi_gpu \
|
|
scripts/train_intervention.py \
|
|
--config configs/intervention_config.yaml \
|
|
--train-data data/processed/train.jsonl
|
|
|
|
# ── Step 5: Evaluate ────────────────────────────────────────────────────
|
|
echo ""
|
|
echo "[5/5] Evaluating..."
|
|
python scripts/evaluate.py \
|
|
--detector-ckpt checkpoints/detector/best.pt \
|
|
--agent-ckpt checkpoints/intervention/final.pt \
|
|
--test-data data/processed/test.jsonl \
|
|
--config configs/detector_config.yaml \
|
|
--intervention-config configs/intervention_config.yaml \
|
|
--output experiments/eval_results.json
|
|
|
|
echo ""
|
|
echo "======================================================"
|
|
echo " Pipeline complete. Results: experiments/eval_results.json"
|
|
echo "======================================================"
|