[paths] train = null dev = null vectors = null init_tok2vec = null [system] gpu_allocator = null seed = 0 [nlp] lang = "en" pipeline = ["tok2vec","tagger","parser","attribute_ruler","lemmatizer","ner"] disabled = ["senter"] before_creation = null after_creation = null after_pipeline_creation = null batch_size = 256 tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"} [components] [components.attribute_ruler] source = "en_core_web_lg" [components.lemmatizer] source = "en_core_web_lg" [components.ner] source = "en_core_web_lg" [components.parser] source = "en_core_web_lg" replace_listeners = ["model.tok2vec"] [components.tagger] source = "en_core_web_lg" replace_listeners = ["model.tok2vec"] [components.tok2vec] source = "en_core_web_lg" [corpora] @readers = "prodigy.MergedCorpus.v1" eval_split = 0.2 sample_size = 1.0 [corpora.ner] @readers = "prodigy.NERCorpus.v1" datasets = ["nas_ner_DrugVirus_Gold_1"] eval_datasets = [] default_fill = "outside" incorrect_key = "incorrect_spans" [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 = 20000 eval_frequency = 200 frozen_components = ["tagger","parser","attribute_ruler","lemmatizer"] 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.ConsoleLogger.v1" progress_bar = false [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] ents_f = 1.0 ents_p = 0.0 ents_r = 0.0 ents_per_type = null [pretraining] [initialize] vectors = "en_core_web_lg" init_tok2vec = ${paths.init_tok2vec} vocab_data = null lookups = null before_init = null after_init = null [initialize.components] [initialize.tokenizer]