Created by: wuhaijun2018

平台：paddlecloud 单机：auc 0.76 多机：auc 从0.6逐渐下降至0.52左右 optimizer ：adam embedding：IS_SPARSE

多机配置： if is_local: train_loop(fluid.default_main_program()) else: port = os.getenv("PADDLE_PORT", "6174") pserver_ips = os.getenv("PADDLE_PSERVERS") # ip,ip... eplist = [] for ip in pserver_ips.split(","): eplist.append(':'.join([ip, port])) pserver_endpoints = ",".join(eplist) # ip:port,ip:port... trainers = int(os.getenv("PADDLE_TRAINERS_NUM", "0")) current_endpoint = os.getenv("POD_IP") + ":" + port trainer_id = int(os.getenv("PADDLE_TRAINER_ID", "0")) t = fluid.DistributeTranspiler() t.transpile(trainer_id, pservers=pserver_endpoints, trainers=trainers) if training_role == "PSERVER": pserver_prog = t.get_pserver_program(current_endpoint) pserver_startup = t.get_startup_program(current_endpoint, pserver_prog) exe.run(pserver_startup) exe.run(pserver_prog) elif training_role == "TRAINER": train_loop(t.get_trainer_program())