| [paths] | |
| train = "corpus/train/grc_perseus-ud-train.spacy" | |
| dev = "corpus/dev/grc_perseus-ud-dev.spacy" | |
| vectors = "vectors/large" | |
| init_tok2vec = "data/pretrained_weights/model32.bin" | |
| raw_text = "raw_text" | |
| [system] | |
| gpu_allocator = null | |
| seed = 0 | |
| [nlp] | |
| lang = "grc" | |
| pipeline = ["tok2vec","morphologizer","tagger","parser","lemmatizer","ner","attribute_ruler"] | |
| batch_size = 128 | |
| disabled = [] | |
| before_creation = null | |
| after_creation = null | |
| after_pipeline_creation = null | |
| tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"} | |
| vectors = {"@vectors":"spacy.Vectors.v1"} | |
| [components] | |
| [components.attribute_ruler] | |
| factory = "attribute_ruler" | |
| scorer = {"@scorers":"spacy.attribute_ruler_scorer.v1"} | |
| validate = false | |
| [components.lemmatizer] | |
| factory = "trainable_lemmatizer" | |
| backoff = "orth" | |
| min_tree_freq = 1 | |
| overwrite = false | |
| scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"} | |
| top_k = 5 | |
| [components.lemmatizer.model] | |
| @architectures = "spacy.Tagger.v2" | |
| nO = null | |
| normalize = false | |
| [components.lemmatizer.model.tok2vec] | |
| @architectures = "spacy.HashEmbedCNN.v2" | |
| pretrained_vectors = true | |
| width = 96 | |
| depth = 4 | |
| embed_size = 2000 | |
| window_size = 1 | |
| maxout_pieces = 3 | |
| subword_features = true | |
| [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 = "tok2vec" | |
| [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.Tok2VecListener.v1" | |
| width = ${components.tok2vec.model.encode.width} | |
| upstream = "tok2vec" | |
| [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 = "tok2vec" | |
| [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 = "tok2vec" | |
| [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 = true | |
| [components.tok2vec.model.encode] | |
| @architectures = "spacy.MaxoutWindowEncoder.v2" | |
| width = 256 | |
| depth = 8 | |
| 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.pretrain] | |
| @readers = "spacy.JsonlCorpus.v1" | |
| path = ${paths.raw_text} | |
| min_length = 5 | |
| max_length = 500 | |
| limit = 0 | |
| [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 = 5000 | |
| max_epochs = 0 | |
| max_steps = 20000 | |
| eval_frequency = 1000 | |
| frozen_components = ["lemmatizer"] | |
| annotating_components = [] | |
| before_to_disk = null | |
| 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.WandbLogger.v3" | |
| project_name = "greCy" | |
| remove_config_values = ["paths.train","paths.dev","corpora.train.path","corpora.dev.path"] | |
| log_dataset_dir = "./corpus" | |
| model_log_interval = 1000 | |
| entity = null | |
| run_name = 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] | |
| pos_acc = 0.04 | |
| morph_acc = 0.04 | |
| morph_per_feat = null | |
| tag_acc = 0.08 | |
| dep_uas = 0.04 | |
| dep_las = 0.04 | |
| dep_las_per_type = null | |
| sents_p = null | |
| sents_r = null | |
| sents_f = null | |
| lemma_acc = 0.38 | |
| ents_f = 0.38 | |
| ents_p = 0.0 | |
| ents_r = 0.0 | |
| ents_per_type = null | |
| [pretraining] | |
| max_epochs = 100 | |
| dropout = 0.2 | |
| n_save_every = null | |
| n_save_epoch = null | |
| component = "tok2vec" | |
| layer = "" | |
| corpus = "corpora.pretrain" | |
| [pretraining.batcher] | |
| @batchers = "spacy.batch_by_words.v1" | |
| size = 3000 | |
| discard_oversize = false | |
| tolerance = 0.2 | |
| get_length = null | |
| [pretraining.objective] | |
| @architectures = "spacy.PretrainCharacters.v1" | |
| maxout_pieces = 3 | |
| hidden_size = 300 | |
| n_characters = 4 | |
| [pretraining.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 | |
| [initialize] | |
| vectors = ${paths.vectors} | |
| init_tok2vec = ${paths.init_tok2vec} | |
| vocab_data = null | |
| lookups = null | |
| before_init = null | |
| after_init = null | |
| [initialize.components] | |
| [initialize.components.attribute_ruler] | |
| [initialize.components.attribute_ruler.patterns] | |
| @readers = "srsly.read_json.v1" | |
| path = "data/augments/attribute_ruler_patterns.json" | |
| [initialize.components.parser] | |
| [initialize.components.parser.labels] | |
| @readers = "spacy.read_labels.v1" | |
| path = "corpus/labels/parser.json" | |
| require = false | |
| [initialize.components.tagger] | |
| [initialize.components.tagger.labels] | |
| @readers = "spacy.read_labels.v1" | |
| path = "corpus/labels/tagger.json" | |
| require = false | |
| [initialize.tokenizer] |