run-16B.sh

#!/bin/bash
#SBATCH -p tydexclu01
#SBATCH -N 16
#SBATCH --cpus-per-task=1
#SBATCH --ntasks-per-node=32
#SBATCH --mem 0
#SBATCH --gres=dcu:4
#SBATCH -J gpt2
#SBATCH -o logs/gpt2-16B-%j.out
#SBATCH -e logs/gpt2-16B-%j.out
ulimit -u 200000
export NCCL_IB_HCA=mlx5
export NCCL_SOCKET_IFNAME=ib0
export HSA_FORCE_FINE_GRAIN_PCIE=1
export OMP_NUM_THREADS=1
echo "START TIME: $(date)"

rm -f ./hostfile/*
rm -f core.*

hostfile=./hostfile/$SLURM_JOB_ID
scontrol show hostnames $SLURM_JOB_NODELIST > ${hostfile}
for i in `cat $hostfile`
do
    echo ${i} slots=4 >> `pwd`/hostfile/hostfile-dl-$SLURM_JOB_ID
done
np=$(cat $hostfile|sort|uniq |wc -l)
np=$(($np*4))
nodename=$(cat $hostfile |sed -n "1p")
dist_url=`echo $nodename | awk '{print $1}'`
mpirun -np $np --allow-run-as-root --hostfile hostfile/hostfile-dl-$SLURM_JOB_ID --bind-to none `pwd`/single-16B.sh $dist_url