crf.json

{
    "dataset_reader": {
        "type": "conll2003",
        "tag_label": "ner",
        "token_indexers": {
            "tokens": {
                "type": "single_id",
                "lowercase_tokens": true
            },
            "token_characters": {
                "type": "characters"
            }
        }
    },
    "train_data_path": "~/test_allen/eng.train",
    "validation_data_path": "~/test_allen/eng.testa",
    "test_data_path": "~/test_allen/eng.testb",
    "evaluate_on_test": true,
    "model": {
        "type": "crf_tagger",
        "text_field_embedder": {
            "tokens": {
                "type": "embedding",
                "embedding_dim": 50,
                "pretrained_file": "https://s3-us-west-2.amazonaws.com/allennlp/datasets/glove/glove.6B.50d.txt.gz",
                "trainable": true
            },
            "token_characters": {
                "type": "character_encoding",
                "embedding": {
                    "embedding_dim": 25
                },
                "encoder": {
                    "type": "gru",
                    "input_size": 25,
                    "hidden_size": 80,
                    "num_layers": 2,
                    "dropout": 0.25,
                    "bidirectional": true
                }
            }
        },
        "encoder": {
            "type": "gru",
            "input_size": 210,
            "hidden_size": 300,
            "num_layers": 2,
            "dropout": 0.5,
            "bidirectional": true
        },
        "regularizer": [
            [
                "transitions$",
                {
                    "type": "l2",
                    "alpha": 0.01
                }
            ]
        ]
    },
    "iterator": {
        "type": "basic",
        "batch_size": 32
    },
    "trainer": {
        "optimizer": "adam",
        "num_epochs": 50,
        "patience": 10,
        "cuda_device": -1
    }
}