CompanionGuard-RL/code/scripts/run_detector.sh

#!/bin/bash
# Train Module B (Risk Detector) on 4x RTX 5090.
#
# Usage:
#   bash scripts/run_detector.sh
#   bash scripts/run_detector.sh --config configs/detector_config.yaml
#
# NVLink not required: DDP communicates via PCIe (sufficient for MacBERT-large).
# Mixed precision: BF16 (native on RTX 5090, ~2x throughput vs FP32).

set -e

CONFIG="${1:---config configs/detector_config.yaml}"
NUM_GPUS=4

echo "=============================================="
echo " CompanionGuard-RL — Module B: Detector"
echo " GPUs      : ${NUM_GPUS}x RTX 5090 (PCIe DDP)"
echo " Precision : BF16"
echo " Config    : ${CONFIG}"
echo "=============================================="

# Verify GPU count
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_detector.py ${CONFIG}