run_train.sh

#!/bin/bash
#SBATCH -p kshdnormal01
#SBATCH -N 4
#SBATCH --cpus-per-task=1
#SBATCH --ntasks-per-node=32
#SBATCH --mem 100G
#SBATCH --gres=dcu:4
#SBATCH -J chatglm
#SBATCH -o logs/pt-%j.out
#SBATCH -e logs/pt-%j.err
ulimit -u 200000

export OMP_NUM_THREADS=1
export NCCL_DEBUG=INFO
export MIOPEN_FIND_MODE=3
export HSA_FORCE_FINE_GRAIN_PCIE=1
export MIOPEN_COMPILE_PARALLEL_LEVEL=1
export NCCL_PLUGIN_P2P=ucx
export NCCL_SOCKET_IFNAME=ib0
export NCCL_P2P_LEVEL=5
export NCCL_NET_PLUGIN=none
unset RCCL_NCHANNELS
unset NCCL_NET_GDR_LEVEL
rm -rf ./hostfile/*

echo "START TIME: $(date)"
hostfile=./hostfile/$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}'`
echo ${dist_url}
mpirun -np $np --hostfile hostfile/hostfile-dl-$SLURM_JOB_ID --bind-to none `pwd`/run_train_single.sh $dist_url