config.yml

# WARNING:
# Do not use this file as is! It only lists and documents available options
# without caring about their consistency.

# The directory where models and summaries will be saved. It is created if it does not exist.
model_dir: cond_gru_exp_deep

data:
  # (required for train_and_eval and train run types).
  train_features_file: data/train.bpe.50000.en
  train_labels_file: data/train.bpe.50000.it

  # (required for train_end_eval and eval run types).
  eval_features_file: data/test.bpe.50000.en
  eval_labels_file: data/test.tok.it

  # (optional) Models may require additional resource files (e.g. vocabularies).
  source_words_vocabulary: data/vocab.bpe.50000.en
  target_words_vocabulary: data/vocab.bpe.50000.it
  # source_tokenizer_config: big_deen_exp/tokenizer.yml
  # target_tokenizer_config: big_deen_exp/tokenizer.yml

# Model and optimization parameters.
params:
  average_loss_in_time: true
  beam_width: 8
  optimizer: AdamOptimizer
  learning_rate: 0.0001
  clip_gradients: 5.0
  decay_type: exponential_decay
  decay_rate: 0.9
  decay_steps: 20000
  start_decay_steps: 500000
  minimum_learning_rate: 0.00001
  label_smoothing: 0.1
  length_penalty: 0.3
  maximum_iterations: 70


# Training options.
train:
  batch_size: 100
  # (optional) Batch size is the number of "examples" or "tokens" (default: "examples").
  batch_type: examples
  # (optional) Save a checkpoint every this many steps.
  save_checkpoints_steps: 10000
  # (optional) How many checkpoints to keep on disk.
  keep_checkpoint_max: 30
  # (optional) Save summaries every this many steps.
  save_summary_steps: 200
  # (optional) Train for this many steps. If not set, train forever.
  train_steps: 600000
  # (optional) If true, makes a single pass over the training data (default: false).
  single_pass: false
  # (optional) The maximum length of feature sequences during training (default: None).
  maximum_features_length: 51
  # (optional) The maximum length of label sequences during training (default: None).
  maximum_labels_length: 51
  # (optional) The width of the length buckets to select batch candidates from (default: 5).
  bucket_width: 5
  # (optional) The number of threads to use for processing data in parallel (default: 4).
  num_threads: 4
  # (optional) The number of elements from which to sample during shuffling (default: 500000).
  # Consider setting this to the number of training examples.
  sample_buffer_size: 4547174
  # (optional) The number of batches to prefetch asynchronously (default: 1).
  prefetch_buffer_size: 1

# (optional) Evaluation options.
eval:
  # (optional) The batch size to use (default: 32).
  batch_size: 30
  # (optional) The number of threads to use for processing data in parallel (default: 1).
  num_threads: 2
  # (optional) The number of batches to prefetch asynchronously (default: 1).
  prefetch_buffer_size: 1
  # (optional) Evaluate every this many seconds (default: 18000).
  eval_delay: 3000
  # (optional) Save evaluation predictions in model_dir/eval/.
  save_eval_predictions: True
  # (optional) Evalutator or list of evaluators that are called on the saved evaluation predictions.
  # Available evaluators: BLEU, BLEU-detok
  external_evaluators: BLEU
  postprocess_script: /home/deep-babelscape/nmt/OpenNMT-tf/iten_exp_2/postprocess-dev.sh
  save_models: False


  # (optional) Inference options.
infer:
  # (optional) The batch size to use (default: 1).
  batch_size: 100
  # (optional) The number of threads to use for processing data in parallel (default: 1).
  num_threads: 1
  # (optional) The number of batches to prefetch asynchronously (default: 1).
  prefetch_buffer_size: 1
  # (optional) For compatible models, the number of hypotheses to output (default: 1).
  n_best: 1