!ModelConfig
config_data: !DataConfig
  data_statistics: !DataStatistics
    average_len_target_per_bucket:
    - 6.1072836910204265
    - 13.428153313951197
    - 23.23116577395051
    - 32.39229990788272
    - 41.42441404260506
    - 50.367542658020426
    - 59.48511314373994
    - 68.5776544063769
    - 73.10567579439002
    - 72.53528702860062
    - 72.67112462006065
    buckets:
    - !!python/tuple
      - 10
      - 10
    - !!python/tuple
      - 20
      - 20
    - !!python/tuple
      - 30
      - 30
    - !!python/tuple
      - 40
      - 40
    - !!python/tuple
      - 50
      - 50
    - !!python/tuple
      - 60
      - 60
    - !!python/tuple
      - 70
      - 70
    - !!python/tuple
      - 80
      - 80
    - !!python/tuple
      - 90
      - 90
    - !!python/tuple
      - 100
      - 100
    - !!python/tuple
      - 101
      - 101
    length_ratio_mean: 1.0516757269625427
    length_ratio_std: 0.3163695955026073
    max_observed_len_source: 101
    max_observed_len_target: 101
    num_discarded: 22693
    num_sents: 51134116
    num_sents_per_bucket:
    - 21705918
    - 12611716
    - 6459477
    - 4425999
    - 2759117
    - 1600168
    - 881180
    - 488678
    - 166197
    - 34021
    - 1645
    num_tokens_source: 897943901
    num_tokens_target: 890903752
    num_unks_source: 73021
    num_unks_target: 27008
    size_vocab_source: 30004
    size_vocab_target: 30004
  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: 30004
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: 30004
lhuc: false
vocab_source_size: 30004
vocab_target_size: 30004
weight_normalization: false
weight_tying: false
weight_tying_type: null
