!ModelConfig
config_data: !DataConfig
  data_statistics: !DataStatistics
    average_len_target_per_bucket:
    - 5.084965511368489
    - 13.632908031565762
    - 22.770816982903042
    - 31.589853914049318
    - 40.0527555346211
    - 48.25670855159552
    - 56.652183173588845
    - 65.41922825376041
    - 72.85698650127688
    - 77.97569444444457
    - 82.78217821782178
    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: 0.9971319222175437
    length_ratio_std: 0.39084860411958205
    max_observed_len_source: 101
    max_observed_len_target: 101
    num_discarded: 786
    num_sents: 353456
    num_sents_per_bucket:
    - 46972
    - 67795
    - 64983
    - 58801
    - 46706
    - 31117
    - 18780
    - 10703
    - 5482
    - 2016
    - 101
    num_tokens_source: 10785408
    num_tokens_target: 10201705
    num_unks_source: 8300
    num_unks_target: 2376
    size_vocab_source: 4004
    size_vocab_target: 4004
  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: 256
  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: 256
  num_factors: 1
  source_factors_combine: concat
  vocab_size: 4004
config_embed_target: !EmbeddingConfig
  dropout: 0.0
  dtype: float32
  factor_configs: null
  num_embed: 256
  num_factors: 1
  source_factors_combine: concat
  vocab_size: 4004
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: 256
  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: 4004
lhuc: false
vocab_source_size: 4004
vocab_target_size: 4004
weight_normalization: false
weight_tying: false
weight_tying_type: null
