corpus/config.cfg

[paths]
train = null
dev = null
vectors = "en_core_web_lg"
init_tok2vec = null

[system]
gpu_allocator = null
seed = 0

[nlp]
lang = "en"
pipeline = ["tok2vec","tagger","parser","attribute_ruler","lemmatizer","ner","textcat_multilabel"]
disabled = ["senter"]
before_creation = null
after_creation = null
after_pipeline_creation = null
batch_size = 256
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
vectors = {"@vectors":"spacy.Vectors.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.textcat_multilabel]
factory = "textcat_multilabel"
scorer = {"@scorers":"spacy.textcat_multilabel_scorer.v2"}
threshold = 0.5

[components.textcat_multilabel.model]
@architectures = "spacy.TextCatEnsemble.v2"
nO = null

[components.textcat_multilabel.model.linear_model]
@architectures = "spacy.TextCatBOW.v3"
exclusive_classes = false
length = 262144
ngram_size = 1
no_output_layer = false
nO = null

[components.textcat_multilabel.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = 96
upstream = "*"

[components.tok2vec]
source = "en_core_web_lg"

[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 = 0
gold_preproc = false
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 = 1
patience = 5000
max_epochs = 0
max_steps = 100000
eval_frequency = 1000
frozen_components = ["tagger","parser","attribute_ruler","lemmatizer","ner"]
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.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]
tag_acc = 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 = null
ents_p = null
ents_r = null
ents_per_type = null
speed = 0.0

[pretraining]

[initialize]
vectors = ${paths.vectors}
init_tok2vec = ${paths.init_tok2vec}
vocab_data = null
lookups = null
after_init = null

[initialize.before_init]
@callbacks = "spacy.copy_from_base_model.v1"
tokenizer = "en_core_web_lg"
vocab = "en_core_web_lg"

[initialize.components]

[initialize.components.ner]

[initialize.components.ner.labels]
@readers = "spacy.read_labels.v1"
path = "corpus/labels/ner.json"

[initialize.components.parser]

[initialize.components.parser.labels]
@readers = "spacy.read_labels.v1"
path = "corpus/labels/parser.json"

[initialize.components.tagger]

[initialize.components.tagger.labels]
@readers = "spacy.read_labels.v1"
path = "corpus/labels/tagger.json"

[initialize.components.textcat_multilabel]

[initialize.components.textcat_multilabel.labels]
@readers = "spacy.read_labels.v1"
path = "corpus/labels/textcat_multilabel.json"

[initialize.tokenizer]