#!/bin/bash
# Directed sex (llm_directed) on an L40S (46 GB) — breed recombinant offspring + select on the verifier.
# Reuses the cached 7B specialist adapters (models/llm/spec_*) if present. Same env as the other LLM
# jobs (see hpc/README.md): uv sync --extra dev --extra neural --extra llm + pre-download the 7B base.
#   submit:  qsub hpc/llm_directed.pbs      status: qstat -u $USER
#PBS -l select=1:ncpus=8:mem=64gb:ngpus=1:gpu_type=L40S
#PBS -l walltime=02:00:00
#PBS -N lam_llm_directed

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

source .venv/bin/activate
nvidia-smi --query-gpu=name,memory.total,driver_version --format=csv,noheader

python -m llm.experiment configs/llm/directed_hpc.yaml

# results/llm_directed_hpc/ written in-place (parquet gitignored). Sync back to plot:
#   rsync -avz hpc:'…/LamarckianAI/results/llm_directed_hpc/' results/llm_directed_hpc/
echo "done: $(date)"