#!/bin/bash
# The HARD-benchmark firm-up on an L40S (46 GB): runs moe_hard_hpc then directed_hard_hpc in one job.
# moe trains the hard specialists (cached spec_*_hard); directed reuses them — so training happens once
# and both experiments share it. Harder tasks (multi-step lists, Caesar ciphers, multi-step arith) keep
# 7B off saturation, giving routing/fusion/selection real headroom to separate — the fair test the easy
# 7B runs could not provide. Same env as the other LLM jobs (see hpc/README.md).
#   submit:  qsub hpc/llm_hard.pbs      status: qstat -u $USER
#PBS -l select=1:ncpus=8:mem=64gb:ngpus=1:gpu_type=L40S
#PBS -l walltime=01:00:00
#PBS -N lam_llm_hard

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/moe_hard_hpc.yaml        # trains spec_*_hard + fusion/union
python -m llm.experiment configs/llm/directed_hard_hpc.yaml   # reuses spec_*_hard + offspring select

# results/{llm_moe_hard_hpc,llm_directed_hard_hpc}/ written in-place (parquet gitignored). Sync back:
#   rsync -avz hpc:'…/results/llm_moe_hard_hpc/' results/llm_moe_hard_hpc/
#   rsync -avz hpc:'…/results/llm_directed_hard_hpc/' results/llm_directed_hard_hpc/
echo "done: $(date)"