# 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.

# 轮数
epochs: 4
# 设备
device: cpu
# 工作目录
workspace: "paddlerec.models.match.dssm"

# dataset列表
dataset:
- name: dataset_train # 名字，用来区分不同的dataset
  batch_size: 4
  type: QueueDataset
  data_path: "{workspace}/data/train" # 数据路径
  data_converter: "{workspace}/synthetic_reader.py"
#- name: dataset_infer # 名字，用来区分不同的dataset
#  batch_size: 1
#  type: QueueDataset
#  data_path: "{workspace}/data/train" # 数据路径
#  data_converter: "{workspace}/synthetic_evaluate_reader.py"

# 超参数
hyper_parameters:
  #优化器
  optimizer:
    class: sgd
    learning_rate: 0.01
    strategy: async
  # 用户自定义
  TRIGRAM_D: 1000
  NEG: 4
  fc_sizes: [300, 300, 128]
  fc_acts: ['tanh', 'tanh', 'tanh']

# executor配置
epoch:
  name:
  trainer_class: single
  save_checkpoint_interval: 2 # 保存模型
  save_inference_interval: 4 # 保存预测模型
  save_checkpoint_path: "increment" # 保存模型路径
  save_inference_path: "inference" # 保存预测模型路径
  save_inference_feed_varnames: ["query", "doc_pos"] # 预测模型feed vars
  save_inference_fetch_varnames: ["cos_sim_0.tmp_0"] # 预测模型 fetch vars
  #init_model_path: "xxxx" # 加载模型

# 执行器，每轮要跑的所有模型
executor:
 - name: train
   model: "{workspace}/model.py" # 模型路径
   dataset_name: dataset_train # 名字，用来区分不同的阶段
   thread_num: 1 # 线程数
   is_infer: False # 是否是infer
# - name: infer
#   model: "{workspace}/model.py" # 模型路径
#   dataset_name: dataset_infer # 名字，用来区分不同的阶段
#   thread_num: 1 # 线程数
#   is_infer: True # 是否是infer