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.
#workspace: "models/recall/word2vec"
runner:
  train_data_dir: "../../../datasets/one_billion/data/all_train"
  train_reader_path: "word2vec_reader" # importlib format
  use_gpu: True
  train_batch_size: 100
  epochs: 5
  print_interval: 100
  #model_init_path: "output_model/0" # init model
  model_save_path: "output_model_word2vec_all"
  test_data_dir: "../../../datasets/one_billion/data/all_test"
  infer_batch_size: 1024
  infer_reader_path: "word2vec_infer_reader" # importlib format
  infer_load_path: "output_model_word2vec_all"
  infer_start_epoch: 0
  infer_end_epoch: 5
  # dataset
  word_count_dict_path: "../../../datasets/one_billion/data/all_dict/word_count_dict.txt"
  word_id_dict_path: "../../../datasets/one_billion/data/all_dict/word_id_dict.txt"

hyper_parameters:
  optimizer:
    learning_rate: 1.0
    decay_steps: 100000
    decay_rate: 0.999
    class: sgd
    strategy: async
  sparse_feature_number: 354051
  sparse_feature_dim: 300
  with_shuffle_batch: False
  neg_num: 5
  window_size: 5