| [paths] | |
| train = null | |
| dev = null | |
| vectors = null | |
| init_tok2vec = null | |
| [system] | |
| gpu_allocator = "pytorch" | |
| seed = 1 | |
| [nlp] | |
| lang = "en" | |
| pipeline = ["transformer","tagger","parser","attribute_ruler","lemmatizer","ner","entity_ruler"] | |
| disabled = [] | |
| before_creation = null | |
| after_creation = null | |
| after_pipeline_creation = null | |
| batch_size = 64 | |
| 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.entity_ruler] | |
| factory = "entity_ruler" | |
| ent_id_sep = "||" | |
| matcher_fuzzy_compare = {"@misc":"spacy.levenshtein_compare.v1"} | |
| overwrite_ents = false | |
| phrase_matcher_attr = null | |
| scorer = {"@scorers":"spacy.entity_ruler_scorer.v1"} | |
| validate = false | |
| [components.lemmatizer] | |
| factory = "lemmatizer" | |
| mode = "rule" | |
| model = null | |
| overwrite = false | |
| scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"} | |
| [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 = false | |
| nO = null | |
| [components.ner.model.tok2vec] | |
| @architectures = "spacy-curated-transformers.LastTransformerLayerListener.v1" | |
| width = ${components.transformer.model.hidden_width} | |
| upstream = "transformer" | |
| pooling = {"@layers":"reduce_mean.v1"} | |
| grad_factor = 1.0 | |
| [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 = false | |
| nO = null | |
| [components.parser.model.tok2vec] | |
| @architectures = "spacy-curated-transformers.LastTransformerLayerListener.v1" | |
| width = ${components.transformer.model.hidden_width} | |
| upstream = "transformer" | |
| pooling = {"@layers":"reduce_mean.v1"} | |
| grad_factor = 1.0 | |
| [components.tagger] | |
| factory = "tagger" | |
| label_smoothing = 0.0 | |
| neg_prefix = "!" | |
| overwrite = false | |
| scorer = {"@scorers":"spacy.tagger_scorer.v1"} | |
| [components.tagger.model] | |
| @architectures = "spacy.Tagger.v2" | |
| nO = null | |
| normalize = false | |
| [components.tagger.model.tok2vec] | |
| @architectures = "spacy-curated-transformers.LastTransformerLayerListener.v1" | |
| width = ${components.transformer.model.hidden_width} | |
| upstream = "transformer" | |
| pooling = {"@layers":"reduce_mean.v1"} | |
| grad_factor = 1.0 | |
| [components.transformer] | |
| factory = "curated_transformer" | |
| all_layer_outputs = false | |
| frozen = false | |
| [components.transformer.model] | |
| @architectures = "spacy-curated-transformers.RobertaTransformer.v1" | |
| vocab_size = 50265 | |
| hidden_width = 768 | |
| piece_encoder = {"@architectures":"spacy-curated-transformers.ByteBpeEncoder.v1"} | |
| attention_probs_dropout_prob = 0.1 | |
| hidden_act = "gelu" | |
| hidden_dropout_prob = 0.1 | |
| intermediate_width = 3072 | |
| layer_norm_eps = 0.00001 | |
| max_position_embeddings = 514 | |
| model_max_length = 512 | |
| num_attention_heads = 12 | |
| num_hidden_layers = 12 | |
| padding_idx = 1 | |
| type_vocab_size = 1 | |
| torchscript = false | |
| mixed_precision = false | |
| wrapped_listener = null | |
| [components.transformer.model.grad_scaler_config] | |
| [components.transformer.model.with_spans] | |
| @architectures = "spacy-curated-transformers.WithStridedSpans.v1" | |
| stride = 104 | |
| window = 144 | |
| batch_size = 384 | |
| [corpora] | |
| [corpora.dev] | |
| @readers = "spacy.Corpus.v1" | |
| path = ${paths.dev} | |
| gold_preproc = false | |
| max_length = 0 | |
| limit = 0 | |
| augmenter = null | |
| [corpora.train] | |
| @readers = "spacy.Corpus.v1" | |
| path = ${paths.train} | |
| gold_preproc = false | |
| max_length = 0 | |
| limit = 0 | |
| augmenter = null | |
| [training] | |
| train_corpus = "corpora.train" | |
| dev_corpus = "corpora.dev" | |
| seed = ${system:seed} | |
| gpu_allocator = ${system:gpu_allocator} | |
| dropout = 0.1 | |
| accumulate_gradient = 3 | |
| patience = 5000 | |
| max_epochs = 0 | |
| max_steps = 20000 | |
| eval_frequency = 1000 | |
| frozen_components = [] | |
| before_to_disk = null | |
| annotating_components = [] | |
| before_update = null | |
| [training.batcher] | |
| @batchers = "spacy.batch_by_words.v1" | |
| discard_oversize = false | |
| size = 2000 | |
| tolerance = 0.2 | |
| get_length = null | |
| [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 = true | |
| eps = 0.00000001 | |
| [training.optimizer.learn_rate] | |
| @schedules = "warmup_linear.v1" | |
| warmup_steps = 250 | |
| total_steps = 20000 | |
| initial_rate = 0.00005 | |
| [training.score_weights] | |
| tag_acc = 0.16 | |
| dep_uas = 0.0 | |
| dep_las = 0.16 | |
| dep_las_per_type = null | |
| sents_p = null | |
| sents_r = null | |
| sents_f = 0.02 | |
| lemma_acc = 0.5 | |
| ents_f = 0.16 | |
| ents_p = 0.0 | |
| ents_r = 0.0 | |
| ents_per_type = null | |
| speed = 0.0 | |
| [pretraining] | |
| [initialize] | |
| vocab_data = null | |
| vectors = ${paths.vectors} | |
| init_tok2vec = ${paths.init_tok2vec} | |
| before_init = null | |
| after_init = null | |
| [initialize.components] | |
| [initialize.components.ner] | |
| [initialize.components.ner.labels] | |
| @readers = "spacy.read_labels.v1" | |
| path = "corpus/labels/ner.json" | |
| require = false | |
| [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.components.transformer] | |
| [initialize.components.transformer.encoder_loader] | |
| @model_loaders = "spacy-curated-transformers.HFTransformerEncoderLoader.v1" | |
| name = "roberta-base" | |
| revision = "main" | |
| [initialize.components.transformer.piecer_loader] | |
| @model_loaders = "spacy-curated-transformers.HFPieceEncoderLoader.v1" | |
| name = "roberta-base" | |
| revision = "main" | |
| [initialize.lookups] | |
| @misc = "spacy.LookupsDataLoader.v1" | |
| lang = ${nlp.lang} | |
| tables = ["lexeme_norm"] | |
| [initialize.tokenizer] |