config_bigdata.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.


runner:
  train_data_dir: "./data/all_data/train_data"
  train_reader_path: "amazon_reader" # importlib format
  use_gpu: True
  use_auc: True
  train_batch_size: 256
  epochs: 7
  print_interval: 2
  #model_init_path: "output_model/0" # init model
  model_save_path: "output_model_bst_bigdata"
  test_data_dir: "./data/all_data/test_data"
  infer_reader_path: "amazon_reader" # importlib format
  infer_batch_size: 256
  infer_load_path: "output_model_bst_bigdata"
  infer_start_epoch: 6
  infer_end_epoch: 7


# hyper parameters of user-defined network
hyper_parameters:
  # optimizer config
  optimizer:
    class: SGD
    learning_rate: 0.0001
  # user-defined <key, value> pairs
  distributed_embedding: 0
  use_DataLoader: True
  item_emb_size: 96
  cat_emb_size: 96
  position_emb_size: 96
  is_sparse: True
  item_count: 63001
  user_count: 192403
  cat_count: 801
  position_count: 5001
  n_encoder_layers: 1
  d_model: 288
  d_key: 48
  d_value: 48
  n_head: 6
  dropout_rate: 0.2
  postprocess_cmd: "da"
  preprocess_cmd: "n"
  prepostprocess_dropout: 0.2
  d_inner_hid: 512
  relu_dropout: 0.2
  act: "relu"
  fc_sizes: [1024, 512, 256]