config.cfg

[paths]
train = null
dev = null
vectors = "vectors/all_text_he_fasttext_model_50"
init_tok2vec = "models/pretrain_ref_he_50/model8.bin"
raw_text = null
input_collection = "merged_output"
output_collection = "gilyon_input"

[system]
gpu_allocator = null
seed = 61
min_len = 20
train_perc = 0.5

[nlp]
lang = "he"
pipeline = ["tok2vec","ner"]
batch_size = 200
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
tokenizer = {"@tokenizers":"inner_punct_tokenizer"}

[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 = 32
maxout_pieces = 3
use_upper = true
nO = null

[components.ner.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = ${components.tok2vec.model.encode.width}
upstream = "*"

[components.tok2vec]
factory = "tok2vec"

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

[components.tok2vec.model.embed]
@architectures = "spacy.MultiHashEmbed.v1"
width = ${components.tok2vec.model.encode.width}
attrs = ["NORM","PREFIX","SUFFIX","ORTH"]
rows = [5000,5000,5000,5000]
include_static_vectors = true

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

[corpora]

[corpora.dev]
@readers = "mongo_reader"
db_host = "localhost"
db_port = 27017
input_collection = ${paths.input_collection}
output_collection = ${paths.output_collection}
train_perc = ${system.train_perc}
corpus_type = "test"
min_len = ${system.min_len}
random_state = ${system.seed}
unique_by_metadata = true

[corpora.pretrain]
@readers = "spacy.JsonlCorpus.v1"
path = ${paths.raw_text}
min_length = 5
max_length = 512
limit = 0

[corpora.train]
@readers = "mongo_reader"
db_host = "localhost"
db_port = 27017
input_collection = ${paths.input_collection}
output_collection = ${paths.output_collection}
train_perc = ${system.train_perc}
corpus_type = "train"
min_len = ${system.min_len}
random_state = ${system.seed}
unique_by_metadata = true

[training]
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
seed = ${system.seed}
gpu_allocator = ${system.gpu_allocator}
dropout = 0.5
accumulate_gradient = 1
patience = 1600
max_epochs = 0
max_steps = 20000
eval_frequency = 200
frozen_components = []
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 = 2000
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 = 0.0007

[training.score_weights]
ents_f = 1.0
ents_p = 0.0
ents_r = 0.0
ents_per_type = null

[pretraining]
max_epochs = 9
dropout = 0.5
n_save_every = null
n_save_epoch = null
component = "tok2vec"
layer = ""
corpus = "corpora.pretrain"

[pretraining.batcher]
@batchers = "spacy.batch_by_words.v1"
size = 10000
discard_oversize = false
tolerance = 0.2
get_length = null

[pretraining.objective]
@architectures = "spacy.PretrainCharacters.v1"
maxout_pieces = 3
hidden_size = 50
n_characters = 4

[pretraining.optimizer]
@optimizers = "Adam.v1"
beta1 = 0.9
beta2 = 0.999
L2_is_weight_decay = true
L2 = 0.01
grad_clip = 1.0
use_averages = true
eps = 0.00000001
learn_rate = 0.001

[initialize]
vectors = ${paths.vectors}
init_tok2vec = ${paths.init_tok2vec}
vocab_data = null
lookups = null
before_init = null
after_init = null

[initialize.components]

[initialize.tokenizer]