config.cfg

[paths]
train = "corpus/classify-train.spacy"
dev = "corpus/classify-test.spacy"
vectors = "en_core_web_lg"
init_tok2vec = null

[variables]
wandb_project_name = "tako-query-filter"
wandb_team_name = "tako-team"

[system]
gpu_allocator = "pytorch"
seed = 0

[nlp]
lang = "en"
pipeline = ["tok2vec","ner","textcat","textcat_classify"]
batch_size = 1000
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
vectors = {"@vectors":"spacy.Vectors.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 = 128
maxout_pieces = 3
use_upper = true
nO = null

[components.ner.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = 256
upstream = "*"

[components.textcat]
factory = "textcat"
scorer = {"@scorers":"spacy.textcat_scorer.v2"}
threshold = 0.0

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

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

[components.textcat.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = 256
upstream = "*"

[components.textcat_classify]
factory = "textcat"
scorer = {"@scorers":"spacy.textcat_scorer.v2"}
threshold = 0.0

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

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

[components.textcat_classify.model.tok2vec]
@architectures = "spacy.Tok2Vec.v2"

[components.textcat_classify.model.tok2vec.embed]
@architectures = "spacy.MultiHashEmbed.v2"
width = 256
attrs = ["NORM","PREFIX","SUFFIX","SHAPE","ENT_TYPE"]
rows = [5000,1000,2500,2500,1000]
include_static_vectors = true

[components.textcat_classify.model.tok2vec.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 256
window_size = 1
maxout_pieces = 3
depth = 8

[components.tok2vec]
factory = "tok2vec"

[components.tok2vec.model]
@architectures = "spacy.Tok2Vec.v2"

[components.tok2vec.model.embed]
@architectures = "spacy.MultiHashEmbed.v2"
width = 256
attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
rows = [5000,1000,2500,2500]
include_static_vectors = true

[components.tok2vec.model.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 256
window_size = 1
maxout_pieces = 3
depth = 8

[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

[corpora.train.augmenter]
@augmenters = "spacy.lower_case.v1"
level = 0.3

[training]
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
seed = ${system.seed}
gpu_allocator = ${system.gpu_allocator}
dropout = 0.1
accumulate_gradient = 1
patience = 3000
max_epochs = 0
max_steps = 20000
eval_frequency = 100
frozen_components = ["tok2vec","ner","textcat"]
annotating_components = ["ner","textcat"]
before_to_disk = null
before_update = null

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

[training.batcher.size]
@schedules = "compounding.v1"
start = 100
stop = 2000
compound = 1.001
t = 0.0

[training.logger]
@loggers = "spacy.ChainLogger.v1"
logger3 = null
logger4 = null
logger5 = null
logger6 = null
logger7 = null
logger8 = null
logger9 = null
logger10 = null

[training.logger.logger1]
@loggers = "spacy.ConsoleLogger.v1"
progress_bar = false

[training.logger.logger2]
@loggers = "spacy.WandbLogger.v5"
project_name = ${variables.wandb_project_name}
remove_config_values = []
model_log_interval = null
log_dataset_dir = null
entity = null
run_name = null
log_best_dir = null
log_latest_dir = null
log_custom_stats = null

[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 = 0.5
ents_p = 0.0
ents_r = 0.0
ents_per_type = null
cats_score = 0.25
cats_score_desc = null
cats_micro_p = null
cats_micro_r = 0.25
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
before_init = null
after_init = null

[initialize.components]

[initialize.components.textcat_classify]
positive_label = "ACCEPT"

[initialize.components.textcat_classify.labels]
@readers = "spacy.read_labels.v1"
path = "corpus/labels/filter-labels/textcat_classify.json"
require = false

[initialize.tokenizer]