code/contrastive_training/step3_train_v51_FIXED_FINAL.sh

#!/bin/bash
#SBATCH --job-name=v51_FIXED
#SBATCH --partition=nova
#SBATCH --nodes=1
#SBATCH --ntasks=1
#SBATCH --cpus-per-task=16
#SBATCH --mem=369G
#SBATCH --gres=gpu:1
#SBATCH --time=48:00:00
#SBATCH --output=v51_FIXED_final_%j.out
#SBATCH --error=v51_FIXED_final_%j.err

echo "==========================================================="
echo "V5.1-FIXED FINAL: Contrastive Training"
echo "==========================================================="
echo "Job ID: $SLURM_JOB_ID"
echo "Started: $(date)"
echo ""
echo "Configuration:"
echo "  Positives: 161,906"
echo "  Negatives: 150,000 (100K rule + 50K model)"
echo "  Loss: 80% MLM + 20% InfoNCE"
echo "  Temperature: 0.1 -> 0.05 (cosine)"
echo "  Curriculum: Easy -> Mixed -> Hard"
echo ""
echo "Bugs Fixed (vs original V5.1):"
echo "  - WURCS patterns for Sialic acid (a2122h, a2212h)"
echo "  - All 8 biological rules working"
echo "  - Model-based negatives included"
echo "  - 0% overlap with positives verified"
echo "==========================================================="

source ~/.bashrc
conda activate glycanml

BASE="/work/ratul1/supantha/glycan-SD-VS/bert_training_v3/v3.1_cluster_training"
cd $BASE/bert_v5.1_contrastive

# Run training with FIXED data
python training/contrastive_trainer_v3_FIXED.py \
    --model_path "$BASE/checkpoints_v5_bpe_topo/best_v5_bpe_topo_model.pt" \
    --positives_path "$BASE/bert_v5.1_contrastive/data/fully_resolved_161k.pkl" \
    --negatives_path "$BASE/bert_v5.1_contrastive/data/hard_negatives_150k_ALL_FINAL.pkl" \
    --output_dir "$BASE/bert_v5.1_contrastive/checkpoints_V51_FIXED_FINAL" \
    --epochs 50 \
    --batch_size 16 \
    --lr 2e-5 \
    --mlm_weight 0.8 \
    --contrastive_weight 0.2 \
    --n_neg 5 \
    --save_interval 5

echo ""
echo "==========================================================="
echo "V5.1-FIXED FINAL: Training Complete"
echo "Finished: $(date)"
echo "==========================================================="