device: "Tesla V100-SXM2-16GB"
base:
  name: "OpenSLUv1"
  train: true
  test: true
  device: cuda
  seed: 42
  epoch_num: 300
  batch_size: 32

model_manager:
  load_dir: null
  save_dir: save/electra-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_: google/electra-small-discriminator
    _padding_side_: right
    add_special_tokens: true
    max_length: 512

optimizer:
  _model_target_: torch.optim.AdamW
  _model_partial_: true
  lr: 2e-5
  weight_decay: 1e-8

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

model:
  _model_target_: model.open_slu_model.OpenSLUModel
  ignore_index: -100
  encoder:
    _model_target_: model.encoder.AutoEncoder
    encoder_name: google/electra-small-discriminator
    output_dim: 256
    return_with_input: true
    return_sentence_level_hidden: true

  decoder:
    _model_target_: model.decoder.base_decoder.BaseDecoder
    intent_classifier:
      _model_target_: model.decoder.classifier.LinearClassifier
      mode: "intent"
      ignore_index: -100


    slot_classifier:
      _model_target_: model.decoder.classifier.LinearClassifier
      mode: "slot"
      ignore_index: -100