#!/bin/bash
# Usage: ./qsub_train.sh [NUM_XPUS]
# Example: ./qsub_train.sh 2

NUM_XPUS=${1:-1}

sbatch <<EOF
#!/bin/bash -l
#SBATCH --job-name=om-train
#SBATCH --account=AIRR-P51-DAWN-GPU
#SBATCH --partition=pvc9
#SBATCH --nodes=1
#SBATCH --gres=gpu:${NUM_XPUS}
#SBATCH -n ${NUM_XPUS}
#SBATCH --time=24:00:00
#SBATCH --output=Logs/train_%j.out
#SBATCH --error=Logs/train_%j.err

. /etc/profile.d/modules.sh
module purge
module load rhel9/default-dawn

source ~/miniconda3/etc/profile.d/conda.sh
conda activate ~/rds/rds-airr-p51-TWhPgQVLKbA/Env/pub_env/pytorch-xpu

echo "Allocated ${NUM_XPUS} XPU(s)"
bash bash_train.sh
EOF