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/multitask/esmm"

dataset:
  - name: dataset_train
    batch_size: 1
    type: QueueDataset
    data_path: "{workspace}/data/train"
    data_converter: "{workspace}/esmm_reader.py"
  - name: dataset_infer
    batch_size: 1
    type: QueueDataset
    data_path: "{workspace}/data/test"
    data_converter: "{workspace}/esmm_reader.py"

hyper_parameters:
  vocab_size: 10000
  embed_size: 128
  optimizer:
    class: adam
    learning_rate: 0.001
    strategy: async

#use infer_runner mode and modify 'phase' below if infer
mode: [train_runner, infer_runner]

runner:
  - name: train_runner
    class: train
    device: cpu
    epochs: 3
    save_checkpoint_interval: 2
    save_inference_interval: 4
    save_checkpoint_path: "increment"
    save_inference_path: "inference"
    print_interval: 10
    phases: [train]
  - name: infer_runner
    class: infer
    init_model_path: "increment/1"
    device: cpu
    print_interval: 1
    phases: [infer]

phase:
  - name: train
    model: "{workspace}/model.py"
    dataset_name: dataset_train
    thread_num: 1
  - name: infer
    model: "{workspace}/model.py"
    dataset_name: dataset_infer
    thread_num: 1