slurm job script example

job_script.sh

#!/bin/bash

# Job name:

#SBATCH --job-name=hilcodec_training

#

# Project:

#SBATCH --account=nn11068k

#

# Wall time limit:

#SBATCH --time=00-00:05:00

#

# Other parameters:

#SBATCH --partition=accel

#SBATCH --gres=gpu:1

#SBATCH --mem=50G

#SBATCH --cpus-per-task=16

# Set up job environment:

set -o errexit # Exit the script on any error

# Initialize Conda without sourcing .bashrc

MINIFORGE_INSTALL_PATH="/cluster/projects/nn11068k/miniforge3"

eval "$($MINIFORGE_INSTALL_PATH/bin/conda shell.bash hook)"

# Load conda environment

ENV_NAME="hilcodec_inductive_bias"

conda activate "$ENV_NAME"

echo "Current Conda environment: $(conda info --envs | grep '*' | awk '{print $1}')"

# Check if PyTorch and CUDA can be loaded

echo "Checking if PyTorch and CUDA are available..."

python -c "

import torch

print(f'PyTorch loaded successfully. Version: {torch.__version__}')

cuda_available = torch.cuda.is_available()

print(f'CUDA available: {cuda_available}')

if cuda_available:

print(f'CUDA device count: {torch.cuda.device_count()}')

print(f'CUDA device name: {torch.cuda.get_device_name(0)}')

"

 

# log in wandb

wandb login MY_API_KEY

# Run Python script

echo "Run the script..."

SCRIPT_FNAME="/cluster/projects/nn11068k/daesoo/hilcodec_inductive_bias/stage1.py"

CKPT_PATH="/cluster/projects/nn11068k/daesoo/hilcodec_inductive_bias/ckpts/epoch=2-step=23320.ckpt"

python "$SCRIPT_FNAME" --ckpt_path "$CKPT_PATH"

The job can be sumibtted by running "$ sbatch job_script.sh"

NB! replace MY_API_KEY