config.cfg

[paths]
train = null
dev = null
vectors = "/opt/anaconda3/envs/spacy/lib/python3.9/site-packages/en_core_sci_md/en_core_sci_md-0.5.4"
init_tok2vec = null

[system]
gpu_allocator = null
seed = 0

[nlp]
lang = "en"
pipeline = ["tok2vec","tagger","attribute_ruler","lemmatizer","parser","ner","textcat_multilabel"]
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.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.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 = 128
maxout_pieces = 3
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"]
rows = [5000,1000,2500,2500]
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 = 128
maxout_pieces = 3
use_upper = true
nO = null

[components.parser.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = 96
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.v2"
nO = null
normalize = "False"

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

[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]
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","IS_SPACE"]
rows = [5000,1000,2500,2500,50,50]
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
ner = null
textcat = null
parser = null
tagger = null
senter = null
spancat = null
experimental_coref = null

[corpora.textcat_multilabel]
@readers = "prodigy.TextCatCorpus.v1"
datasets = ["prodigy_aaa_class"]
eval_datasets = []
exclusive = false

[training]
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
seed = ${system.seed}
gpu_allocator = "pytorch"
dropout = 0.1
accumulate_gradient = 1
patience = 0
max_epochs = 20
max_steps = 0
eval_frequency = 200
frozen_components = ["parser","tagger","attribute_ruler","lemmatizer","ner"]
before_to_disk = null
annotating_components = ["tok2vec","textcat_multilabel"]
before_update = null

[training.batcher]
@batchers = "spacy.batch_by_sequence.v1"
get_length = null

[training.batcher.size]
@schedules = "compounding.v1"
start = 4
stop = 64
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 = false
eps = 0.00000001
learn_rate = 0.001

[training.score_weights]
tag_acc = null
lemma_acc = 0.33
dep_uas = null
dep_las = null
dep_las_per_type = null
sents_p = null
sents_r = null
sents_f = null
ents_f = null
ents_p = null
ents_r = null
ents_per_type = null
cats_score = 0.67
cats_score_desc = null
cats_micro_p = null
cats_micro_r = null
cats_micro_f = null
cats_macro_p = null
cats_macro_r = null
cats_macro_f = null
cats_macro_auc = null
cats_f_per_type = null

[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 = "/opt/anaconda3/envs/spacy/lib/python3.9/site-packages/en_core_sci_md/en_core_sci_md-0.5.4"
vocab = "/opt/anaconda3/envs/spacy/lib/python3.9/site-packages/en_core_sci_md/en_core_sci_md-0.5.4"

[initialize.components]

[initialize.tokenizer]