#!/bin/bash
# Veto-arm replication (prereg tasks/prereg-llm-society-v4.md §8f): the v5 `society` arm with
# "keep the parent unchanged" as an admissible offspring. Seeds 2-3 pair against the existing v5
# isolated/society/seed_bank runs for those seeds. Seed 1 ran locally.
#   submit: qsub hpc/llm_veto.pbs     status: qstat -u $USER -t
#PBS -l select=1:ncpus=8:mem=64gb:ngpus=1:gpu_type=L40S
#PBS -l walltime=04:00:00
#PBS -N lam_veto
#PBS -J 2-3

cd "$PBS_O_WORKDIR"
export HF_HOME="$EPHEMERAL/hf_cache"
export HF_DATASETS_CACHE="$EPHEMERAL/hf_cache/datasets"
export TOKENIZERS_PARALLELISM=false
export PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True

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

CFG="configs/llm/_gen/veto_s${PBS_ARRAY_INDEX}.yaml"
mkdir -p configs/llm/_gen
python - "$PBS_ARRAY_INDEX" "$CFG" <<'PYEOF'
import sys, yaml
seed, out = int(sys.argv[1]), sys.argv[2]
cfg = yaml.safe_load(open("configs/llm/curriculum_v5_veto.yaml"))
cfg["seed"] = seed
cfg["batch_size"] = 48
cfg["train_batch_size"] = 4
cfg["output"] = {"dir": f"results/llm_curriculum_v5_veto/s{seed}"}
yaml.safe_dump(cfg, open(out, "w"), sort_keys=False)
PYEOF

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