Loading env.sh +1 −1 Original line number Diff line number Diff line module load PrgEnv-gnu module load gcc/10.3.0 module load rocm/6.0.0 ROOT=/lustre/orion/world-shared/stf053/olcf-6-benchmark/miniconda3 ROOT=REPLACE_PWD/miniconda3 export PATH=${ROOT}/bin:$PATH source ${ROOT}/etc/profile.d/conda.sh conda activate ${ROOT}/../topaz_env Loading train.py +1 −1 Original line number Diff line number Diff line Loading @@ -253,7 +253,7 @@ if __name__ == "__main__": subsocket.setsockopt_string(zmq.SUBSCRIBE, "metadata") subsocket.setsockopt_string(zmq.SUBSCRIBE, "data") subsocket.setsockopt_string(zmq.SUBSCRIBE, "END") subsocket.connect("tcp://login10.frontier.olcf.ornl.gov:5560") subsocket.connect("tcp://REPLACE_HOST:5560") print(f"Rank-{torch.distributed.get_rank()}: Synchronized; ready to receive data") start_time = datetime.now() Loading Loading
env.sh +1 −1 Original line number Diff line number Diff line module load PrgEnv-gnu module load gcc/10.3.0 module load rocm/6.0.0 ROOT=/lustre/orion/world-shared/stf053/olcf-6-benchmark/miniconda3 ROOT=REPLACE_PWD/miniconda3 export PATH=${ROOT}/bin:$PATH source ${ROOT}/etc/profile.d/conda.sh conda activate ${ROOT}/../topaz_env Loading
train.py +1 −1 Original line number Diff line number Diff line Loading @@ -253,7 +253,7 @@ if __name__ == "__main__": subsocket.setsockopt_string(zmq.SUBSCRIBE, "metadata") subsocket.setsockopt_string(zmq.SUBSCRIBE, "data") subsocket.setsockopt_string(zmq.SUBSCRIBE, "END") subsocket.connect("tcp://login10.frontier.olcf.ornl.gov:5560") subsocket.connect("tcp://REPLACE_HOST:5560") print(f"Rank-{torch.distributed.get_rank()}: Synchronized; ready to receive data") start_time = datetime.now() Loading