# Training hyper-parameters and additional features.
[training]
# Whether to train on sequences with 'gold standard' sentence boundaries
# and tokens. If you set this to true, take care to ensure your run-time
# data is passed in sentence-by-sentence via some prior preprocessing.
gold_preproc = false
# Limitations on training document length or number of examples.
max_length = 5000
limit = 0
# Data augmentation
orth_variant_level = 0.0
dropout = 0.1
# Controls early-stopping. 0 or -1 mean unlimited.
patience = 1600
max_epochs = 0
max_steps = 20000
eval_frequency = 200
# Other settings
seed = 0
accumulate_gradient = 1
use_pytorch_for_gpu_memory = false
# Control how scores are printed and checkpoints are evaluated.
eval_batch_size = 128
score_weights = {"dep_las": 0.4, "ents_f": 0.4, "tag_acc": 0.2}
init_tok2vec = null
discard_oversize = false
batch_by = "words"
raw_text = null
tag_map = null
vectors = null
base_model = null
morph_rules = null

[training.batch_size]
@schedules = "compounding.v1"
start = 100
stop = 1000
compound = 1.001

[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 = 1e-8
learn_rate = 0.001

[nlp]
lang = "en"
load_vocab_data = false
pipeline = ["tok2vec", "ner", "tagger", "parser"]

[nlp.tokenizer]
@tokenizers = "spacy.Tokenizer.v1"

[nlp.lemmatizer]
@lemmatizers = "spacy.Lemmatizer.v1"

[components]

[components.tok2vec]
factory = "tok2vec"

[components.ner]
factory = "ner"
learn_tokens = false
min_action_freq = 1

[components.tagger]
factory = "tagger"

[components.parser]
factory = "parser"
learn_tokens = false
min_action_freq = 30

[components.tagger.model]
@architectures = "spacy.Tagger.v1"

[components.tagger.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = ${components.tok2vec.model.encode:width}

[components.parser.model]
@architectures = "spacy.TransitionBasedParser.v1"
nr_feature_tokens = 8
hidden_width = 128
maxout_pieces = 2
use_upper = true

[components.parser.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = ${components.tok2vec.model.encode:width}

[components.ner.model]
@architectures = "spacy.TransitionBasedParser.v1"
nr_feature_tokens = 3
hidden_width = 128
maxout_pieces = 2
use_upper = true

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

[components.tok2vec.model]
@architectures = "spacy.Tok2Vec.v1"

[components.tok2vec.model.embed]
@architectures = "spacy.MultiHashEmbed.v1"
width = ${components.tok2vec.model.encode:width}
rows = 2000
also_embed_subwords = true
also_use_static_vectors = false

[components.tok2vec.model.encode]
@architectures = "spacy.MaxoutWindowEncoder.v1"
width = 96
depth = 4
window_size = 1
maxout_pieces = 3