{
  "attention": "scaled_luong",
  "attention_architecture": "standard",
  "batch_size": 128,
  "bpe_delimiter": null,
  "colocate_gradients_with_ops": true,
  "decay_factor": 0.5,
  "decay_steps": 1000,
  "dropout": 0.2,
  "encoder_type": "bi",
  "eos": "</s>",
  "forget_bias": 1.0,
  "infer_batch_size": 32,
  "init_weight": 0.1,
  "learning_rate": 1.0,
  "max_gradient_norm": 5.0,
  "metrics": ["bleu"],
  "num_buckets": 5,
  "num_layers": 2,
  "num_train_steps": 12000,
  "num_units": 512,
  "optimizer": "sgd",
  "residual": false,
  "share_vocab": false,
  "sos": "<s>",
  "source_reverse": false,
  "src_max_len": 50,
  "src_max_len_infer": null,
  "start_decay_step": 8000,
  "steps_per_external_eval": null,
  "steps_per_stats": 100,
  "tgt_max_len": 50,
  "tgt_max_len_infer": null,
  "time_major": true,
  "unit_type": "lstm",
  "beam_width": 10
}