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.


workspace: "models/match/dssm"

dataset:
- name: dataset_train
  batch_size: 8
  type: DataLoader # or QueueDataset
  data_path: "{workspace}/data/train" 
  data_converter: "{workspace}/synthetic_reader.py"
- name: dataset_infer
  batch_size: 1
  type: DataLoader # or QueueDataset
  data_path: "{workspace}/data/test"
  data_converter: "{workspace}/synthetic_evaluate_reader.py"

hyper_parameters:
  optimizer:
    class: sgd
    learning_rate: 0.001
    strategy: async
  trigram_d: 1439
  neg_num: 1
  fc_sizes: [300, 300, 128]
  fc_acts: ['tanh', 'tanh', 'tanh']

mode: [train_runner,infer_runner]
# config of each runner.
# runner is a kind of paddle training class, which wraps the train/infer process.
runner:
- name: train_runner
  class: train
  # num of epochs
  epochs: 3
  # device to run training or infer
  device: cpu
  save_checkpoint_interval: 1 # save model interval of epochs
  save_inference_interval: 1 # save inference
  save_checkpoint_path: "increment" # save checkpoint path
  save_inference_path: "inference" # save inference path
  save_inference_feed_varnames: ["query", "doc_pos"] # feed vars of save inference
  save_inference_fetch_varnames: ["cos_sim_0.tmp_0"] # fetch vars of save inference
  init_model_path: "" # load model path
  print_interval: 2
  phases: phase1
- name: infer_runner
  class: infer
  # device to run training or infer
  device: cpu
  print_interval: 1
  init_model_path: "increment/2" # load model path
  phases: phase2

# runner will run all the phase in each epoch
phase:
- name: phase1
  model: "{workspace}/model.py" # user-defined model
  dataset_name: dataset_train # select dataset by name
  thread_num: 1
- name: phase2
  model: "{workspace}/model.py" # user-defined model
  dataset_name: dataset_infer # select dataset by name
  thread_num: 1