#!/bin/bash
# Differential reproduction in the six-generation population (manuscript revision 2026-09-12):
# configs/llm/curriculum_v5_cull.yaml (isolated + declinable society, both with culling), one element
# per seed 1-3, ~1.5 h each. Output results/llm_curriculum_v5_cull/s{seed}/.
#   submit: qsub hpc/llm_cull.pbs     status: qstat -u $USER -t
#PBS -l select=1:ncpus=8:mem=64gb:ngpus=1:gpu_type=L40S
#PBS -l walltime=03:00:00
#PBS -N lam_cull
#PBS -J 1-3

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"
export PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
source .venv/bin/activate
nvidia-smi --query-gpu=name,memory.total,driver_version --format=csv,noheader
mkdir -p configs/llm/_gen
SEED=$PBS_ARRAY_INDEX
echo "seed=$SEED start=$(date)"
CFG="configs/llm/_gen/curriculum_v5_cull_s${SEED}.yaml"
python - "$SEED" "$CFG" <<'PYEOF'
import sys, yaml
seed, out = int(sys.argv[1]), sys.argv[2]
cfg = yaml.safe_load(open("configs/llm/curriculum_v5_cull.yaml"))
cfg["seed"] = seed
cfg["batch_size"] = 48
cfg["train_batch_size"] = 4
cfg["output"] = {"dir": f"results/llm_curriculum_v5_cull/s{seed}"}
yaml.safe_dump(cfg, open(out, "w"), sort_keys=False)
PYEOF
python -m llm.experiment "$CFG"
echo "done: $(date)"