add paddle cloud run

core/trainers/single_trainer.py

@@ -112,6 +112,7 @@ class SingleTrainer(TranspileTrainer):
                                          fetch_list=self.fetch_vars,
                                          fetch_info=self.fetch_alias,
                                          print_period=self.fetch_period)
+
             self.save(i, "train", is_fleet=False)
         context['status'] = 'infer_pass'
 

example/cloud/config.ini

@@ -14,9 +14,4 @@ train_data_path="/user/paddle/benchmark/ctr/train_data_paddle/part_1*"
 #test_data_path="/user/paddle/benchmark/ctr/test_data"
 
 #the output directory on hdfs
-output_path="/user/paddle/ly"
-
-CPU_NUM=16
-
-GLOG_v=0
-FLAGS_rpc_deadline=300000
+output_path="/user/paddle/ly"
\ No newline at end of file

example/cloud/config.yaml

+# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+train:
+  trainer:
+    # for cluster training
+    strategy: "async"
+
+  epochs: 10
+  workspace: "paddlerec.models.rank.dnn"
+
+  reader:
+    batch_size: 2
+    class: "{workspace}/../criteo_reader.py"
+    train_data_path: "train_data"
+    reader_debug_mode: False
+
+  model:
+    models: "{workspace}/model.py"
+    hyper_parameters:
+      sparse_inputs_slots: 27
+      sparse_feature_number: 1000001
+      sparse_feature_dim: 9
+      dense_input_dim: 13
+      fc_sizes: [512, 256, 128, 32]
+      learning_rate: 0.001
+      optimizer: adam
+
+  save:
+    increment:
+      dirname: "increment"
+      epoch_interval: 2
+      save_last: True
+    inference:
+      dirname: "inference"
+      epoch_interval: 4
+      save_last: True

example/cloud/job.sh

 #!/bin/bash
 
 ###################################################
-# Usage: submit.sh
-# Description: run mpi submit clinet implement
+# Usage: job.sh
+# Description: run mpi job clinet implement
 ###################################################
 
-echo "heheda"
+
+# ---------------------------------------------------------------------------- #
+#                            variable define                                   #
+# ---------------------------------------------------------------------------- #
+CPU_NUM=16
+GLOG_v=0
+FLAGS_rpc_deadline=300000
+# ---------------------------------------------------------------------------- #
 
 python -m paddlerec.run -m paddle_rec_config.yaml -e cluster -r worker

example/cloud/submit.sh

@@ -39,5 +39,5 @@ function package() {
   cp ${engine_run_config} ${temp}/paddle_rec_config.yaml
 
   g_submitfiles="job.sh before_hook.sh paddle_rec_config.yaml"
-  g_run_cmd='"sh job.sh"'
+  g_run_cmd="sh job.sh"
 }