!ModelConfig
config_data: !DataConfig
  data_statistics: !DataStatistics
    average_len_target_per_bucket:
    - 6.224099949119744
    - 11.900929390242466
    - 18.856174790324257
    - 25.362565896437903
    - 32.32720165555296
    - 35.44430379746838
    - 33.623287671232866
    - 34.10526315789473
    - 24.888888888888886
    - 41.5
    - null
    - null
    buckets:
    - !!python/tuple
      - 9
      - 10
    - !!python/tuple
      - 18
      - 20
    - !!python/tuple
      - 27
      - 30
    - !!python/tuple
      - 36
      - 40
    - !!python/tuple
      - 45
      - 50
    - !!python/tuple
      - 54
      - 60
    - !!python/tuple
      - 63
      - 70
    - !!python/tuple
      - 72
      - 80
    - !!python/tuple
      - 81
      - 90
    - !!python/tuple
      - 90
      - 100
    - !!python/tuple
      - 99
      - 101
    - !!python/tuple
      - 101
      - 101
    length_ratio_mean: 1.1497443504588851
    length_ratio_std: 0.5457667234589977
    max_observed_len_source: 86
    max_observed_len_target: 79
    num_discarded: 1
    num_sents: 1383673
    num_sents_per_bucket:
    - 715404
    - 543905
    - 98724
    - 20297
    - 4349
    - 790
    - 146
    - 38
    - 18
    - 2
    - 0
    - 0
    num_tokens_source: 13088684
    num_tokens_target: 13477390
    num_unks_source: 13925
    num_unks_target: 0
    size_vocab_source: 30004
    size_vocab_target: 29403
  max_seq_len_source: 101
  max_seq_len_target: 101
  num_source_factors: 1
  source_with_eos: true
config_decoder: !TransformerConfig
  act_type: relu
  attention_heads: 8
  conv_config: null
  dropout_act: 0.1
  dropout_attention: 0.1
  dropout_prepost: 0.1
  dtype: float32
  feed_forward_num_hidden: 1024
  lhuc: false
  max_seq_len_source: 101
  max_seq_len_target: 101
  model_size: 512
  num_layers: 4
  positional_embedding_type: fixed
  postprocess_sequence: dr
  preprocess_sequence: n
  use_lhuc: false
config_embed_source: !EmbeddingConfig
  dropout: 0.0
  dtype: float32
  factor_configs: null
  num_embed: 512
  num_factors: 1
  source_factors_combine: concat
  vocab_size: 30004
config_embed_target: !EmbeddingConfig
  dropout: 0.0
  dtype: float32
  factor_configs: null
  num_embed: 512
  num_factors: 1
  source_factors_combine: concat
  vocab_size: 29403
config_encoder: !TransformerConfig
  act_type: relu
  attention_heads: 8
  conv_config: null
  dropout_act: 0.1
  dropout_attention: 0.1
  dropout_prepost: 0.1
  dtype: float32
  feed_forward_num_hidden: 1024
  lhuc: false
  max_seq_len_source: 101
  max_seq_len_target: 101
  model_size: 512
  num_layers: 4
  positional_embedding_type: fixed
  postprocess_sequence: dr
  preprocess_sequence: n
  use_lhuc: false
config_loss: !LossConfig
  label_smoothing: 0.1
  name: cross-entropy
  normalization_type: valid
  vocab_size: 29403
lhuc: false
vocab_source_size: 30004
vocab_target_size: 29403
weight_normalization: false
weight_tying: false
weight_tying_type: null
