device: "Tesla V100-SXM2-16GB"

base:
  name: "OpenSLUv1"
  train: true
  test: true
  device: cuda
  seed: 42
  epoch_num: 300
  batch_size: 16

model_manager:
  load_dir: null
  save_dir: save/stack-propagation-snips

evaluator:
  best_key: EMA
  eval_by_epoch: true
  # eval_step: 1800
  metric:
    - intent_acc
    - slot_f1
    - EMA

accelerator:
  use_accelerator: false

dataset:
  dataset_name: snips

tokenizer:
    _tokenizer_name_: word_tokenizer
    _padding_side_: right
    _align_mode_: fast
    add_special_tokens: false
    max_length: 512

optimizer:
  _model_target_: torch.optim.Adam
  _model_partial_: true
  lr: 0.001
  weight_decay: 1e-6

scheduler:
  _model_target_: transformers.get_scheduler
  _model_partial_: true
  name : "linear"
  num_warmup_steps: 0

model:
  _model_target_: model.OpenSLUModel

  encoder:
    _model_target_: model.encoder.AutoEncoder
    encoder_name: self-attention-lstm

    embedding:
      embedding_dim: 256
      dropout_rate: 0.4

    lstm:
      layer_num: 1
      bidirectional: true
      output_dim: 256
      dropout_rate: 0.4

    attention:
      hidden_dim: 1024
      output_dim: 128
      dropout_rate: 0.4

    return_with_input: true
    return_sentence_level_hidden: false

  decoder:
    _model_target_: model.decoder.StackPropagationDecoder
    interaction:
      _model_target_: model.decoder.interaction.StackInteraction
      differentiable: false

    intent_classifier:
      _model_target_: model.decoder.classifier.AutoregressiveLSTMClassifier
      layer_num: 1
      bidirectional: false
      force_ratio: 0.9
      hidden_dim: 64
      embedding_dim: 8
      ignore_index: -100
      dropout_rate: 0.4
      mode: "token-level-intent"
      use_multi: false
      return_sentence_level: true

    slot_classifier:
      _model_target_: model.decoder.classifier.AutoregressiveLSTMClassifier
      layer_num: 1
      bidirectional: false
      force_ratio: 0.9
      hidden_dim: 64
      embedding_dim: 32
      ignore_index: -100
      dropout_rate: 0.4
      mode: "slot"
      use_multi: false
      return_sentence_level: false