andreids's picture
Update spaCy pipeline
6b35d82
[paths]
train = "corpus/train.spacy"
dev = "corpus/dev.spacy"
vectors = null
init_tok2vec = null
[system]
seed = 0
gpu_allocator = null
[nlp]
lang = "en"
pipeline = ["textcat"]
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
batch_size = 1000
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
[components]
[components.textcat]
factory = "textcat"
scorer = {"@scorers":"spacy.textcat_scorer.v1"}
threshold = 0.5
[components.textcat.model]
@architectures = "spacy.TextCatEnsemble.v2"
nO = null
[components.textcat.model.linear_model]
@architectures = "spacy.TextCatBOW.v1"
exclusive_classes = true
ngram_size = 1
no_output_layer = false
nO = null
[components.textcat.model.tok2vec]
@architectures = "spacy.Tok2Vec.v2"
[components.textcat.model.tok2vec.embed]
@architectures = "spacy.MultiHashEmbed.v1"
width = 64
rows = [2000,2000,1000,1000,1000,1000]
attrs = ["ORTH","LOWER","PREFIX","SUFFIX","SHAPE","ID"]
include_static_vectors = false
[components.textcat.model.tok2vec.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 64
window_size = 1
maxout_pieces = 3
depth = 2
[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 = 1000
max_epochs = 0
max_steps = 1000
eval_frequency = 100
frozen_components = []
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
before_to_disk = null
annotating_components = []
[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]
cats_score = null
cats_score_desc = null
cats_micro_p = 0.5
cats_micro_r = null
cats_micro_f = null
cats_macro_p = 0.5
cats_macro_r = null
cats_macro_f = null
cats_macro_auc = null
cats_f_per_type = null
cats_macro_auc_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]
[initialize.tokenizer]