#!/bin/bash
# Seeds 2-3 of the LLM speciation tier (manuscript revision 2026-09-12; Fig. 5C-D was single-seed).
# One element per seed; output results/llm_speciation/s{seed}/ (seed 1 moved to s1/). Adapters go to
# a seed-specific scratch dir, so the elements can run concurrently.
#   submit: qsub hpc/llm_speciation_seeds.pbs     status: qstat -u $USER -t
#PBS -l select=1:ncpus=8:mem=64gb:ngpus=1:gpu_type=L40S
#PBS -l walltime=01:30:00
#PBS -N lam_spec_seeds
#PBS -J 2-3

cd "$PBS_O_WORKDIR"
export HF_HOME="$EPHEMERAL/hf_cache"
export HF_DATASETS_CACHE="$EPHEMERAL/hf_cache/datasets"
export TOKENIZERS_PARALLELISM=false
export UV_CACHE_DIR="$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=$(date)"
CFG="configs/llm/_gen/speciation_s${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/speciation.yaml"))
cfg["seed"] = seed
cfg["batch_size"] = 32                        # L40S: 46 GB
cfg["output"] = {"dir": f"results/llm_speciation/s{seed}"}
yaml.safe_dump(cfg, open(out, "w"), sort_keys=False)
PYEOF
python -m llm.experiment "$CFG"
echo "done: $(date)"