code/probes/cluster_scripts/run_novel_probes.sh

#!/bin/bash
#SBATCH --job-name=novel_probes
#SBATCH --partition=nova
#SBATCH --gres=gpu:1
#SBATCH --cpus-per-task=8
#SBATCH --mem=32G
#SBATCH --time=02:00:00
#SBATCH --output=bert_v6_contrastive/scripts/novel_probes_%j.out
#SBATCH --error=bert_v6_contrastive/scripts/novel_probes_%j.err

echo "========================================"
echo "Novel Embedding Probes"
echo "Job ID: $SLURM_JOB_ID"
echo "Node: $(hostname)"
echo "Started: $(date)"
echo "========================================"

cd /work/ratul1/supantha/glycan-SD-VS/bert_training_v3/v3.1_cluster_training
source /work/ratul1/supantha/miniconda3/etc/profile.d/conda.sh
conda activate glycan_bert 2>/dev/null || source activate glycan_bert 2>/dev/null || true
pip install -q scikit-learn umap-learn scipy 2>/dev/null

SCRIPT=bert_v6_contrastive/scripts/novel_probes.py

echo ""
echo "========== V5 — All 7 Novel Probes =========="
python3 $SCRIPT --model v5 --probe all --max_samples 2000

echo ""
echo "Generated files:"
ls -la bert_v6_contrastive/analysis/novel_probes_v5/ 2>/dev/null
echo ""
echo "Completed: $(date)"