[paths]
train = ""
dev = ""
vectors = null
vocab_data = null
init_tok2vec = null

[system]
seed = 0
gpu_allocator = null

[nlp]
lang = null
pipeline = []
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null

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

[components]

# Readers for corpora like dev and train.
[corpora]

[corpora.train]
@readers = "spacy.Corpus.v1"
path = ${paths.train}
# 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
max_length = 0
# Limitation on number of training examples
limit = 0
# Apply some simply data augmentation, where we replace tokens with variations.
# This is especially useful for punctuation and case replacement, to help
# generalize beyond corpora that don't have smart-quotes, or only have smart
# quotes, etc.
augmenter = {"@augmenters": "spacy.orth_variants.v1", "level": 0.1, "lower": 0.5}

[corpora.dev]
@readers = "spacy.Corpus.v1"
path = ${paths.dev}
# 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
max_length = 0
# Limitation on number of training examples
limit = 0

# Training hyper-parameters and additional features.
[training]
seed = ${system.seed}
gpu_allocator = ${system.gpu_allocator}
dropout = 0.1
accumulate_gradient = 1
# Controls early-stopping. 0 or -1 mean unlimited.
patience = 1600
max_epochs = 0
max_steps = 20000
eval_frequency = 200
# Control how scores are printed and checkpoints are evaluated.
score_weights = {}
# Names of pipeline components that shouldn't be updated during training
frozen_components = []
# Location in the config where the dev corpus is defined
dev_corpus = "corpora.dev"
# Location in the config where the train corpus is defined
train_corpus = "corpora.train"
# Optional callback before nlp object is saved to disk after training
before_to_disk = null

[training.logger]
@loggers = "spacy.ConsoleLogger.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

[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

# The 'initialize' step is run before training or pretraining. Components and
# the tokenizer can each define their own arguments via their .initialize
# methods that are populated by the config. This lets them gather resources like
# lookup tables and build label sets, construct vocabularies, etc.
[initialize]
vocab_data = ${paths.vocab_data}
lookups = null
vectors = ${paths.vectors}
# Extra resources for transfer-learning or pseudo-rehearsal
init_tok2vec = ${paths.init_tok2vec}
# Arguments passed to the tokenizer's initialize method
tokenizer = {}
# Arguments passed to the initialize methods of the components (keyed by component name)
components = {}