| [paths] | |
| train = "assets/train.spacy" | |
| dev = "assets/dev.spacy" | |
| vectors = null | |
| init_tok2vec = null | |
| [system] | |
| gpu_allocator = null | |
| seed = 0 | |
| [nlp] | |
| lang = "en" | |
| pipeline = ["tok2vec","spancat"] | |
| batch_size = 1000 | |
| disabled = [] | |
| before_creation = null | |
| after_creation = null | |
| after_pipeline_creation = null | |
| tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"} | |
| [components] | |
| [components.spancat] | |
| factory = "spancat" | |
| max_positive = null | |
| scorer = {"@scorers":"spacy.spancat_scorer.v1"} | |
| spans_key = "sc" | |
| threshold = 0.5 | |
| [components.spancat.model] | |
| @architectures = "spacy.SpanCategorizer.v1" | |
| [components.spancat.model.reducer] | |
| @layers = "spacy.mean_max_reducer.v1" | |
| hidden_size = 128 | |
| [components.spancat.model.scorer] | |
| @layers = "spacy.LinearLogistic.v1" | |
| nO = null | |
| nI = null | |
| [components.spancat.model.tok2vec] | |
| @architectures = "spacy.Tok2VecListener.v1" | |
| width = ${components.tok2vec.model.encode.width} | |
| upstream = "*" | |
| [components.spancat.suggester] | |
| @misc = "spacy.ngram_range_suggester.v1" | |
| min_size = 1 | |
| max_size = 20 | |
| [components.tok2vec] | |
| factory = "tok2vec" | |
| [components.tok2vec.model] | |
| @architectures = "spacy.Tok2Vec.v2" | |
| [components.tok2vec.model.embed] | |
| @architectures = "spacy.MultiHashEmbed.v2" | |
| width = ${components.tok2vec.model.encode.width} | |
| attrs = ["NORM","PREFIX","SUFFIX","SHAPE"] | |
| rows = [5000,2500,2500,2500] | |
| include_static_vectors = false | |
| [components.tok2vec.model.encode] | |
| @architectures = "spacy.MaxoutWindowEncoder.v2" | |
| width = 96 | |
| depth = 4 | |
| window_size = 1 | |
| maxout_pieces = 3 | |
| [corpora] | |
| [corpora.dev] | |
| @readers = "spacy.Corpus.v1" | |
| path = ${paths.dev} | |
| max_length = 0 | |
| gold_preproc = false | |
| limit = 0 | |
| augmenter = null | |
| [corpora.train] | |
| @readers = "spacy.Corpus.v1" | |
| path = ${paths.train} | |
| max_length = 0 | |
| gold_preproc = false | |
| limit = 0 | |
| augmenter = null | |
| [training] | |
| dev_corpus = "corpora.dev" | |
| train_corpus = "corpora.train" | |
| seed = ${system.seed} | |
| gpu_allocator = ${system.gpu_allocator} | |
| dropout = 0.1 | |
| accumulate_gradient = 1 | |
| patience = 1600 | |
| max_epochs = 0 | |
| max_steps = 20 | |
| eval_frequency = 200 | |
| frozen_components = [] | |
| annotating_components = [] | |
| before_to_disk = null | |
| [training.batcher] | |
| @batchers = "spacy.batch_by_words.v1" | |
| discard_oversize = false | |
| tolerance = 0.2 | |
| get_length = null | |
| [training.batcher.size] | |
| @schedules = "compounding.v1" | |
| start = 100 | |
| stop = 1000 | |
| compound = 1.001 | |
| t = 0.0 | |
| [training.logger] | |
| @loggers = "spacy.WandbLogger.v4" | |
| project_name = "pubmed_spancat_training" | |
| remove_config_values = ["paths.train","paths.dev","corpora.train.path","corpora.dev.path"] | |
| log_dataset_dir = "./assets" | |
| log_best_dir = "./training/spancat/model-best" | |
| model_log_interval = 10 | |
| entity = null | |
| run_name = null | |
| log_latest_dir = null | |
| [training.optimizer] | |
| @optimizers = "Adam.v1" | |
| beta1 = 0.9 | |
| beta2 = 0.999 | |
| L2_is_weight_decay = true | |
| L2 = 0.01 | |
| grad_clip = 1.0 | |
| use_averages = false | |
| eps = 0.00000001 | |
| learn_rate = 0.001 | |
| [training.score_weights] | |
| spans_sc_f = 1.0 | |
| spans_sc_p = 0.0 | |
| spans_sc_r = 0.0 | |
| [pretraining] | |
| [initialize] | |
| vectors = ${paths.vectors} | |
| init_tok2vec = ${paths.init_tok2vec} | |
| vocab_data = null | |
| lookups = null | |
| before_init = null | |
| after_init = null | |
| [initialize.components] | |
| [initialize.components.spancat] | |
| [initialize.components.spancat.labels] | |
| @readers = "spacy.read_labels.v1" | |
| path = "test/labels/spancat.json" | |
| require = false | |
| [initialize.tokenizer] |