Files
CompanionGuard-RL/code/scripts/run_intervention.sh
zhangsiyuan bd1f51c496 chore: initial commit — unified project repo
Merged code repo (CompanionGuard-RL) into single project-level git.
Reorganized root: docs/, reference/, experiments/, tmp/active|archives/.
Gitignored: data/, checkpoints/, .venv, experiment logs, tmp/archives.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-14 11:28:42 +08:00

38 lines
1.1 KiB
Bash

#!/bin/bash
# Train Module C (Intervention Policy) on 4x RTX 5090.
#
# Stage 1 — Behavior Cloning: all 4 GPUs (DDP, BF16)
# Stage 2 — PPO fine-tuning: GPU-0 only (inherently sequential)
#
# Usage:
# bash scripts/run_intervention.sh
# bash scripts/run_intervention.sh data/processed/train.jsonl
set -e
TRAIN_DATA="${1:-data/processed/train.jsonl}"
CONFIG="configs/intervention_config.yaml"
NUM_GPUS=4
echo "=============================================="
echo " CompanionGuard-RL — Module C: Intervention"
echo " Stage 1 (BC) : ${NUM_GPUS}x GPU (DDP, BF16)"
echo " Stage 2 (PPO) : GPU-0 only"
echo " Config : ${CONFIG}"
echo " Train data : ${TRAIN_DATA}"
echo "=============================================="
ACTUAL_GPUS=$(nvidia-smi --query-gpu=name --format=csv,noheader | wc -l)
if [ "$ACTUAL_GPUS" -lt "$NUM_GPUS" ]; then
echo "[WARN] Expected ${NUM_GPUS} GPUs, found ${ACTUAL_GPUS}. Adjusting."
NUM_GPUS=$ACTUAL_GPUS
fi
accelerate launch \
--num_processes=${NUM_GPUS} \
--mixed_precision=bf16 \
--multi_gpu \
scripts/train_intervention.py \
--config ${CONFIG} \
--train-data ${TRAIN_DATA}