distrib_search.sh (1195B)
1 #!/bin/bash 2 #SBATCH -A lco@gpu 3 #SBATCH --job-name=mmsrl # job name 4 #SBATCH --ntasks=1 # number of MP tasks 5 #SBATCH --ntasks-per-node=1 # number of MPI tasks per node 6 #SBATCH --gres=gpu:1 # number of GPUs per node 7 #SBATCH --cpus-per-task=10 # number of cores per tasks 8 #SBATCH --hint=nomultithread # we get physical cores not logical 9 #SBATCH --distribution=block:block # we pin the tasks on contiguous cores 10 #SBATCH --time=5:00:00 # maximum execution time (HH:MM:SS) 11 #SBATCH --output=new_old_freq_%j_%x_%A_%a.out # output file name 12 #SBATCH --error=new_old_freq_%j_%x_%A_%a.err # error file name 13 #SBATCH --array=0-19 14 15 16 cd $WORK/mmsrl 17 18 module purge 19 source ~/.bashrc 20 conda activate pytorch 21 export DATA_PATH=$WORK/data 22 23 FACTOR=('0.1' '0.3' '0.5' '0.7' '0.9') 24 BIAS=('0.02' '0.05' '0.1' '0.2') 25 ifactor=$(($SLURM_ARRAY_TASK_ID%5)) 26 ibias=$(($SLURM_ARRAY_TASK_ID/5)) 27 python -m mmsrl.train configs/ofa_new_old_best.py --frequency_factor=${FACTOR[$ifactor]} --frequency_bias=${BIAS[$ibias]} --output_val=\"val_${FACTOR[$ifactor]}_${BIAS[$ibias]}.pkl\" --output_test=\"test_${FACTOR[$ifactor]}_${BIAS[$ibias]}.pkl\"