#!/bin/bash #SBATCH --job-name=train_msn_ #SBATCH --output=logs/job.%j.out #SBATCH --error=logs/job.%j.err #SBATCH --partition=gpu #SBATCH --gres=gpu:2 #SBATCH --nodes=1 #SBATCH --mem=48G #SBATCH --ntasks-per-node=2 #number of MPI tasks per node (=number of GPUs per node) #SBATCH --cpus-per-task=1 #SBATCH -t 16:00:00 #SBATCH --mail-user=alexandre.chapin@ec-lyon.fr #SBATCH --mail-typ=FAIL echo ${SLURM_NODELIST} torchrun --standalone --nnodes 1 --nproc_per_node 2 train.py runs/msn/osrt/config.yaml --wandb