decompattn.json

{
  "dataset_reader": {
    "type": "scitail_graph",
    "token_indexers": {
      "tokens": {
        "type": "single_id",
        "lowercase_tokens": true
      }
    },
    "tokenizer": {
      "end_tokens": ["@@NULL@@"]
    }
  },
  "train_data_path":
    "./data/nli_datasets/SciTailV1/tsv_format/conceptnet_processed/triples/parsed/scitail_1.0_train_conceptnet_triples.tsv",
  "validation_data_path":
    "./data/nli_datasets/SciTailV1/tsv_format/conceptnet_processed/triples/parsed/scitail_1.0_dev_conceptnet_triples.tsv",
  "model": {
    "type": "decompattn",
    "text_field_embedder": {
      "tokens": {
        "type": "embedding",
        "projection_dim": 200,
        "pretrained_file": "./data/embeddings/glove/glove.840B.300d.txt.gz",
        "embedding_dim": 300,
        "trainable": false
      }
    },
    "attend_feedforward": {
      "input_dim": 200,
      "num_layers": 2,
      "hidden_dims": 200,
      "activations": "relu",
      "dropout": 0.2
    },
    "similarity_function": { "type": "dot_product" },
    "compare_feedforward": {
      "input_dim": 400,
      "num_layers": 2,
      "hidden_dims": 200,
      "activations": "relu",
      "dropout": 0.2
    },
    "aggregate_feedforward": {
      "input_dim": 400,
      "num_layers": 2,
      "hidden_dims": [200, 2],
      "activations": ["relu", "linear"],
      "dropout": [0.2, 0.0]
    },
    "initializer": [
      [".*linear_layers.*weight", { "type": "xavier_normal" }],
      [
        ".*token_embedder_tokens._projection.*weight",
        { "type": "xavier_normal" }
      ]
    ]
  },
  "iterator": {
    "type": "bucket",
    "sorting_keys": [["premise", "num_tokens"], ["hypothesis", "num_tokens"]],
    "batch_size": 128
  },

  "trainer": {
    "num_epochs": 140,
    "patience": 20,
    "cuda_device": -1,
    "grad_clipping": 5.0,
    "validation_metric": "+accuracy",
    "optimizer": {
      "type": "adam",
      "lr": 0.001
    }
  }
}