train_in1k_deepspeed.sh

#!/usr/bin/env bash

set -x

PARTITION=$1
JOB_NAME=$2
CONFIG=$3
GPUS=${GPUS:-8}
GPUS_PER_NODE=${GPUS_PER_NODE:-8}
CPUS_PER_TASK=${CPUS_PER_TASK:-10}
SRUN_ARGS=${SRUN_ARGS:-""}

PYTHONPATH="$(dirname $0)/..":$PYTHONPATH \
    srun -p ${PARTITION} \
    --job-name=${JOB_NAME} \
    --gres=gpu:${GPUS_PER_NODE} \
    --ntasks=${GPUS} \
    --ntasks-per-node=${GPUS_PER_NODE} \
    --cpus-per-task=${CPUS_PER_TASK} \
    --kill-on-bad-exit=1 \
    --quotatype=spot \
    ${SRUN_ARGS} \
    python -u main_deepspeed.py \
    --cfg ${CONFIG} \
    --local-rank 0 \
    --data-path /mnt/lustre/share/images \
    --output work_dirs_deepspeed ${@:4}