#!/bin/bash
# The composition campaign (prereg tasks/prereg-llm-compose-v3.md): one (seed, arm) per array
# element. Seed 1 runs locally on the A4000 as the hedge; this array covers seeds 2-3 x 3 arms.
# Each element trains its own founders (cached per seed under models/, first writer wins via the
# adapter_config.json check) and checkpoints every generation, so a requeued element resumes.
#   submit:  qsub hpc/llm_compose.pbs        status: qstat -u $USER -t
#   index -> seed = 2 + (i-1)/3, arm = (dry grounded dry_cat)[(i-1)%3]
#PBS -l select=1:ncpus=8:mem=64gb:ngpus=1:gpu_type=L40S
#PBS -l walltime=08:00:00
#PBS -N lam_compose
#PBS -J 1-6

cd "$PBS_O_WORKDIR"
export HF_HOME="$EPHEMERAL/hf_cache"
export HF_DATASETS_CACHE="$EPHEMERAL/hf_cache/datasets"
export TOKENIZERS_PARALLELISM=false
export UV_CACHE_DIR="$EPHEMERAL/uvcache"

ARMS=(dry grounded dry_cat)
I=$((PBS_ARRAY_INDEX - 1))
SEED=$((2 + I / 3))
ARM=${ARMS[$((I % 3))]}

source .venv/bin/activate
nvidia-smi --query-gpu=name,memory.total,driver_version --format=csv,noheader
echo "seed=$SEED arm=$ARM start=$(date)"

CFG="configs/llm/_gen/compose_s${SEED}_${ARM}.yaml"
mkdir -p configs/llm/_gen
python - "$SEED" "$ARM" "$CFG" <<'EOF'
import sys, yaml
seed, arm, out = int(sys.argv[1]), sys.argv[2], sys.argv[3]
cfg = yaml.safe_load(open("configs/llm/compose_s1.yaml"))
cfg["seed"] = seed
cfg["arms"] = [arm]
cfg["batch_size"] = 32          # L40S has 46 GB; the A4000 setting is 16
cfg["score_batch_size"] = 8
cfg["output"] = {"dir": f"results/llm_compose/s{seed}_{arm}"}
yaml.safe_dump(cfg, open(out, "w"), sort_keys=False)
EOF

python -m llm.experiment "$CFG"
echo "done: $(date)"