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
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