| [paths] | |
| train = null | |
| dev = null | |
| vectors = null | |
| init_tok2vec = null | |
| [system] | |
| gpu_allocator = null | |
| seed = 0 | |
| [nlp] | |
| lang = "ca" | |
| pipeline = ["tok2vec","morphologizer","parser","attribute_ruler","lemmatizer","ner"] | |
| disabled = [] | |
| before_creation = null | |
| after_creation = null | |
| after_pipeline_creation = null | |
| batch_size = 256 | |
| tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"} | |
| [components] | |
| [components.attribute_ruler] | |
| factory = "attribute_ruler" | |
| scorer = {"@scorers":"spacy.attribute_ruler_scorer.v1"} | |
| validate = false | |
| [components.lemmatizer] | |
| factory = "lemmatizer" | |
| mode = "rule" | |
| model = null | |
| overwrite = false | |
| scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"} | |
| [components.morphologizer] | |
| factory = "morphologizer" | |
| extend = false | |
| overwrite = true | |
| scorer = {"@scorers":"spacy.morphologizer_scorer.v1"} | |
| [components.morphologizer.model] | |
| @architectures = "spacy.Tagger.v1" | |
| nO = null | |
| [components.morphologizer.model.tok2vec] | |
| @architectures = "spacy.Tok2Vec.v2" | |
| [components.morphologizer.model.tok2vec.embed] | |
| @architectures = "spacy.MultiHashEmbed.v2" | |
| width = 96 | |
| attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"] | |
| rows = [5000,2500,2500,2500,100] | |
| include_static_vectors = true | |
| [components.morphologizer.model.tok2vec.encode] | |
| @architectures = "spacy.MaxoutWindowEncoder.v2" | |
| width = 96 | |
| depth = 4 | |
| window_size = 1 | |
| maxout_pieces = 3 | |
| [components.ner] | |
| factory = "ner" | |
| incorrect_spans_key = null | |
| moves = null | |
| scorer = {"@scorers":"spacy.ner_scorer.v1"} | |
| update_with_oracle_cut_size = 100 | |
| [components.ner.model] | |
| @architectures = "spacy.TransitionBasedParser.v2" | |
| state_type = "ner" | |
| extra_state_tokens = false | |
| hidden_width = 64 | |
| maxout_pieces = 2 | |
| use_upper = true | |
| nO = null | |
| [components.ner.model.tok2vec] | |
| @architectures = "spacy.Tok2Vec.v2" | |
| [components.ner.model.tok2vec.embed] | |
| @architectures = "spacy.MultiHashEmbed.v2" | |
| width = 96 | |
| attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"] | |
| rows = [5000,2500,2500,2500,100] | |
| include_static_vectors = true | |
| [components.ner.model.tok2vec.encode] | |
| @architectures = "spacy.MaxoutWindowEncoder.v2" | |
| width = 96 | |
| depth = 4 | |
| window_size = 1 | |
| maxout_pieces = 3 | |
| [components.parser] | |
| factory = "parser" | |
| learn_tokens = false | |
| min_action_freq = 30 | |
| moves = null | |
| scorer = {"@scorers":"spacy.parser_scorer.v1"} | |
| update_with_oracle_cut_size = 100 | |
| [components.parser.model] | |
| @architectures = "spacy.TransitionBasedParser.v2" | |
| state_type = "parser" | |
| extra_state_tokens = false | |
| hidden_width = 64 | |
| maxout_pieces = 2 | |
| use_upper = true | |
| nO = null | |
| [components.parser.model.tok2vec] | |
| @architectures = "spacy.Tok2Vec.v2" | |
| [components.parser.model.tok2vec.embed] | |
| @architectures = "spacy.MultiHashEmbed.v2" | |
| width = 96 | |
| attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"] | |
| rows = [5000,2500,2500,2500,100] | |
| include_static_vectors = true | |
| [components.parser.model.tok2vec.encode] | |
| @architectures = "spacy.MaxoutWindowEncoder.v2" | |
| width = 96 | |
| depth = 4 | |
| window_size = 1 | |
| maxout_pieces = 3 | |
| [components.tok2vec] | |
| factory = "tok2vec" | |
| [components.tok2vec.model] | |
| @architectures = "spacy.Tok2Vec.v2" | |
| [components.tok2vec.model.embed] | |
| @architectures = "spacy.MultiHashEmbed.v2" | |
| width = 96 | |
| attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"] | |
| rows = [5000,2500,2500,2500,100] | |
| include_static_vectors = true | |
| [components.tok2vec.model.encode] | |
| @architectures = "spacy.MaxoutWindowEncoder.v2" | |
| width = 96 | |
| depth = 4 | |
| window_size = 1 | |
| maxout_pieces = 3 | |
| [corpora] | |
| @readers = "prodigy.MergedCorpus.v1" | |
| eval_split = 0.2 | |
| sample_size = 1.0 | |
| textcat = null | |
| textcat_multilabel = null | |
| parser = null | |
| tagger = null | |
| senter = null | |
| spancat = null | |
| [corpora.ner] | |
| @readers = "prodigy.NERCorpus.v1" | |
| datasets = ["iris_LOC"] | |
| eval_datasets = [] | |
| default_fill = "outside" | |
| incorrect_key = "incorrect_spans" | |
| [training] | |
| train_corpus = "corpora.train" | |
| dev_corpus = "corpora.dev" | |
| seed = ${system:seed} | |
| gpu_allocator = ${system:gpu_allocator} | |
| dropout = 0.1 | |
| accumulate_gradient = 1 | |
| patience = 5000 | |
| max_epochs = 0 | |
| max_steps = 0 | |
| eval_frequency = 1000 | |
| frozen_components = ["morphologizer","parser","attribute_ruler","lemmatizer"] | |
| before_to_disk = null | |
| annotating_components = [] | |
| [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 = "prodigy.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 = true | |
| eps = 0.00000001 | |
| learn_rate = 0.001 | |
| [training.score_weights] | |
| pos_acc = null | |
| morph_acc = null | |
| morph_per_feat = null | |
| dep_uas = null | |
| dep_las = null | |
| dep_las_per_type = null | |
| sents_p = null | |
| sents_r = null | |
| sents_f = null | |
| lemma_acc = null | |
| ents_f = 1.0 | |
| ents_p = 0.0 | |
| ents_r = 0.0 | |
| ents_per_type = null | |
| speed = 0.0 | |
| [pretraining] | |
| [initialize] | |
| vectors = "ca_core_news_lg" | |
| init_tok2vec = ${paths.init_tok2vec} | |
| vocab_data = null | |
| lookups = null | |
| before_init = null | |
| after_init = null | |
| [initialize.components] | |
| [initialize.tokenizer] |