spaCy/spacy/default_config.cfg

[nlp]
lang = null
pipeline = []
load_vocab_data = true

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

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

[components]

# 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
eval_batch_size = 128
# Other settings
seed = 0
accumulate_gradient = 1
use_pytorch_for_gpu_memory = false
# Control how scores are printed and checkpoints are evaluated.
score_weights = {}
# These settings are invalid for the transformer models.
init_tok2vec = null
discard_oversize = false
raw_text = null
tag_map = null
morph_rules = null
base_model = null
vectors = null
batch_by = "words"
batch_size = 1000

[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

[training.optimizer.learn_rate]
@schedules = "warmup_linear.v1"
warmup_steps = 250
total_steps = 20000
initial_rate = 0.001

[pretraining]
max_epochs = 1000
min_length = 5
max_length = 500
dropout = 0.2
n_save_every = null
batch_size = 3000
seed = ${training:seed}
use_pytorch_for_gpu_memory = ${training:use_pytorch_for_gpu_memory}
tok2vec_model = "components.tok2vec.model"

[pretraining.objective]
type = "characters"
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 = 1e-8
learn_rate = 0.001