1
0
mw-lifecycle-analysis/p2/quest/slurm_jobs/parallel_olmo_categorization.sh
2025-09-04 10:12:34 -05:00

34 lines
848 B
Bash

#!/bin/bash
#SBATCH -A p32852
#SBATCH -p gengpu
#SBATCH --gres=gpu:a100:2
#SBATCH --nodes=2
#SBATCH --ntasks-per-node=2
#SBATCH --time=48:00:00
#SBATCH --mem=64G
#SBATCH --cpus-per-task=4
#SBATCH --job-name=MW-info-typology
#SBATCH --output=parallel-mw-olmo-info-cat.log
#SBATCH --mail-type=BEGIN,END,FAIL
#SBATCH --mail-user=gaughan@u.northwestern.edu
module purge
eval "$(conda shell.bash hook)"
echo "setting up the environment by loading in conda environment at $(date)"
conda activate olmo
echo "running the bertopic job at $(date)"
srun torchrun \
--nnodes 2 \
--nproc-per-node 2 \
--rdzv_id $RANDOM \
--rdzv_backend c10d \
--rdzv_endpoint "$SLURMD_NODENAME:29502" \
/home/nws8519/git/mw-lifecycle-analysis/p2/quest/python_scripts/olmo_parallel_cat.py 10000 100
echo "unsupervised olmo categorization pau at $(date)"