#!/bin/bash
# Wait for B's 100-ep stages (stage 2 train + stage 3 best-ckpt inference) to
# release GPU 0, then run the C b-loss-only 100-ep ablation.
source /opt/conda/etc/profile.d/conda.sh && conda activate longitudinal-313
cd /mnt/b4/xfr/git26/longitudinal
echo "waiting for GPU0 (B 100ep stages) at $(date -u)"
while true; do
  mem=$(nvidia-smi --id=0 --query-gpu=memory.used --format=csv,noheader,nounits 2>/dev/null | tr -d ' ')
  util=$(nvidia-smi --id=0 --query-gpu=utilization.gpu --format=csv,noheader,nounits 2>/dev/null | tr -d ' ')
  if [ -n "$mem" ] && [ "$mem" -lt 1000 ] && [ -n "$util" ] && [ "$util" -lt 5 ]; then
    echo "GPU0 free (mem=${mem}MiB util=${util}%) at $(date -u); launching C b-loss-only 100ep"
    break
  fi
  sleep 120
done
python scripts/benchmark_pipelines.py --pipelines C --b-loss-only --gpu 0 --train-epochs 100 \
  --eval-at "5 10 20 50" --workers 4 \
  --out results/benchmark_full/benchmark_full_C_bloss_100ep.json 2>&1 | tee logs/bench_C_bloss_100ep.log
echo "C b-loss-only 100ep finished at $(date -u)"