99 lines
2.2 KiB
INI
99 lines
2.2 KiB
INI
# This is an auto-generated partial config. To use it with 'spacy train'
|
|
# you can run spacy init fill-config to auto-fill all default settings:
|
|
# python -m spacy init fill-config ./base_config.cfg ./config.cfg
|
|
# after filling:
|
|
# python -m spacy train config.cfg --paths.train ./train.spacy --paths.dev ./dev.spacy
|
|
# python -m spacy train config.cfg --output ./output
|
|
[paths]
|
|
train = "./training/231207_train.spacy"
|
|
dev = "./training/231207_dev.spacy"
|
|
vectors = "de_core_news_lg"
|
|
[system]
|
|
gpu_allocator = null
|
|
|
|
[nlp]
|
|
lang = "de"
|
|
pipeline = ["tok2vec","spancat"]
|
|
batch_size = 1000
|
|
|
|
[components]
|
|
|
|
[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, 1000, 2500, 2500]
|
|
include_static_vectors = true
|
|
|
|
[components.tok2vec.model.encode]
|
|
@architectures = "spacy.MaxoutWindowEncoder.v2"
|
|
width = 256
|
|
depth = 8
|
|
window_size = 1
|
|
maxout_pieces = 3
|
|
|
|
[components.spancat]
|
|
factory = "spancat"
|
|
max_positive = null
|
|
scorer = {"@scorers":"spacy.spancat_scorer.v1"}
|
|
spans_key = "sc"
|
|
threshold = 0.5
|
|
|
|
[components.spancat.model]
|
|
@architectures = "spacy.SpanCategorizer.v1"
|
|
|
|
[components.spancat.model.reducer]
|
|
@layers = "spacy.mean_max_reducer.v1"
|
|
hidden_size = 128
|
|
|
|
[components.spancat.model.scorer]
|
|
@layers = "spacy.LinearLogistic.v1"
|
|
nO = null
|
|
nI = null
|
|
|
|
[components.spancat.model.tok2vec]
|
|
@architectures = "spacy.Tok2VecListener.v1"
|
|
width = ${components.tok2vec.model.encode.width}
|
|
|
|
[components.spancat.suggester]
|
|
@misc = "spacy.ngram_suggester.v1"
|
|
sizes = [1,2,3]
|
|
|
|
[corpora]
|
|
|
|
[corpora.train]
|
|
@readers = "spacy.Corpus.v1"
|
|
path = ${paths.train}
|
|
max_length = 0
|
|
|
|
[corpora.dev]
|
|
@readers = "spacy.Corpus.v1"
|
|
path = ${paths.dev}
|
|
max_length = 0
|
|
|
|
[training]
|
|
dev_corpus = "corpora.dev"
|
|
train_corpus = "corpora.train"
|
|
|
|
[training.optimizer]
|
|
@optimizers = "Adam.v1"
|
|
|
|
[training.batcher]
|
|
@batchers = "spacy.batch_by_words.v1"
|
|
discard_oversize = false
|
|
tolerance = 0.2
|
|
|
|
[training.batcher.size]
|
|
@schedules = "compounding.v1"
|
|
start = 100
|
|
stop = 1000
|
|
compound = 1.001
|
|
|
|
[initialize]
|
|
vectors = ${paths.vectors} |