{ "dataset_reader": { "type": "citation_dataset_reader" }, "train_data_path": "data/jsonl/train.jsonl", "validation_data_path": "data/jsonl/dev.jsonl", "test_data_path": "data/jsonl/test.jsonl", "evaluate_on_test": true, "model": { "type": "basic_bilstm_classifier", "text_field_embedder": { "token_embedders": { "tokens": { "pretrained_file": "/mount/arbeitsdaten/studenten1/team-lab-nlp/mandavsi_rileyic/glove.6B.100d.txt.gz", "type": "embedding", "embedding_dim": 100, "trainable": false } } }, "encoder": { "type": "lstm", "input_size": 1124, "hidden_size": 100, "num_layers": 1, "bidirectional": true }, "elmo": { "options_file": "https://s3-us-west-2.amazonaws.com/allennlp/models/elmo/2x4096_512_2048cnn_2xhighway_5.5B/elmo_2x4096_512_2048cnn_2xhighway_5.5B_options.json", "weight_file": "/mount/arbeitsdaten/studenten1/team-lab-nlp/mandavsi_rileyic/elmo_2x4096_512_2048cnn_2xhighway_5.5B_weights.hdf5", "do_layer_norm": true, "dropout": 0.5, "num_output_representations": 1 }, "use_input_elmo": true, "classifier_feedforward": { "input_dim": 200, "num_layers": 2, "hidden_dims": [20, 3], "activations": ["linear", "linear"] } }, "data_loader": { "batch_sampler": { "type": "bucket", "batch_size" : 16 } }, "trainer": { "optimizer": { "type": "adam", "lr": 0.001 }, "num_epochs": 2, "cuda_device": 1 } }