[paths] train = "/tmp/tmpjbbqe3m6/tmp_train.spacy" dev = "/tmp/tmpjbbqe3m6/tmp_dev.spacy" vectors = null init_tok2vec = null [system] gpu_allocator = null seed = 0 [nlp] lang = "fo" pipeline = ["tok2vec","tagger","morphologizer","parser"] tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"} disabled = [] before_creation = null after_creation = null after_pipeline_creation = null batch_size = 1000 vectors = {"@vectors":"spacy.Vectors.v1"} [components] [components.morphologizer] factory = "morphologizer" extend = false label_smoothing = 0.0 overwrite = true scorer = {"@scorers":"spacy.morphologizer_scorer.v1"} [components.morphologizer.model] @architectures = "spacy.Tagger.v1" nO = null [components.morphologizer.model.tok2vec] @architectures = "spacy.Tok2VecListener.v1" width = ${components.tok2vec.model.encode.width} upstream = "*" [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 = 128 maxout_pieces = 3 use_upper = true nO = null [components.parser.model.tok2vec] @architectures = "spacy.Tok2VecListener.v1" width = ${components.tok2vec.model.encode.width} upstream = "*" [components.tagger] factory = "tagger" label_smoothing = 0.0 neg_prefix = "!" overwrite = false scorer = {"@scorers":"spacy.tagger_scorer.v1"} [components.tagger.model] @architectures = "spacy.Tagger.v1" nO = null [components.tagger.model.tok2vec] @architectures = "spacy.Tok2VecListener.v1" width = ${components.tok2vec.model.encode.width} upstream = "*" [components.tok2vec] factory = "tok2vec" [components.tok2vec.model] @architectures = "spacy.Tok2Vec.v2" [components.tok2vec.model.embed] @architectures = "spacy.MultiHashEmbed.v1" width = ${components.tok2vec.model.encode.width} attrs = ["LOWER","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 = 2000 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 = 1400 eval_frequency = 200 frozen_components = [] before_to_disk = null annotating_components = [] before_update = 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] tag_acc = 0.33 pos_acc = 0.17 morph_acc = 0.17 morph_per_feat = null dep_uas = 0.17 dep_las = 0.17 dep_las_per_type = null sents_p = null sents_r = null sents_f = 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.tokenizer]