2022-05-03 18:41:31 +02:00
|
|
|
[paths]
|
|
|
|
|
train = null
|
|
|
|
|
dev = null
|
|
|
|
|
vectors = null
|
|
|
|
|
init_tok2vec = null
|
|
|
|
|
|
|
|
|
|
[system]
|
|
|
|
|
seed = 0
|
|
|
|
|
gpu_allocator = null
|
|
|
|
|
|
|
|
|
|
[nlp]
|
|
|
|
|
lang = "en"
|
|
|
|
|
pipeline = ["ner"]
|
|
|
|
|
disabled = []
|
|
|
|
|
before_creation = null
|
|
|
|
|
after_creation = null
|
|
|
|
|
after_pipeline_creation = null
|
|
|
|
|
batch_size = 1000
|
|
|
|
|
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
|
|
|
|
|
|
|
|
|
|
[components]
|
|
|
|
|
|
|
|
|
|
[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.HashEmbedCNN.v2"
|
|
|
|
|
pretrained_vectors = null
|
|
|
|
|
width = 96
|
|
|
|
|
depth = 4
|
|
|
|
|
embed_size = 2000
|
|
|
|
|
window_size = 1
|
|
|
|
|
maxout_pieces = 3
|
|
|
|
|
subword_features = true
|
|
|
|
|
|
|
|
|
|
[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]
|
|
|
|
|
seed = ${system.seed}
|
|
|
|
|
gpu_allocator = ${system.gpu_allocator}
|
|
|
|
|
dropout = 0.1
|
|
|
|
|
accumulate_gradient = 1
|
|
|
|
|
patience = 1600
|
|
|
|
|
max_epochs = 0
|
|
|
|
|
max_steps = 20000
|
|
|
|
|
eval_frequency = 200
|
|
|
|
|
frozen_components = []
|
|
|
|
|
annotating_components = []
|
|
|
|
|
dev_corpus = "corpora.dev"
|
|
|
|
|
train_corpus = "corpora.train"
|
|
|
|
|
before_to_disk = 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]
|
|
|
|
|
ents_f = 1.0
|
|
|
|
|
ents_p = 0.0
|
|
|
|
|
ents_r = 0.0
|
|
|
|
|
ents_per_type = null
|
|
|
|
|
|
|
|
|
|
[pretraining]
|
|
|
|
|
|
|
|
|
|
[initialize]
|
|
|
|
|
vectors = ${paths.vectors}
|
|
|
|
|
init_tok2vec = ${paths.init_tok2vec}
|
|
|
|
|
vocab_data = null
|
|
|
|
|
lookups = null
|
|
|
|
|
before_init = null
|
|
|
|
|
after_init = null
|
|
|
|
|
|
|
|
|
|
[initialize.components]
|
|
|
|
|
|
2022-05-02 18:54:19 +02:00
|
|
|
[initialize.tokenizer]
|
