spaCy/examples/experiments/onto-ner.cfg
2020-07-06 17:51:37 +02:00

79 lines
1.8 KiB
INI

# 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 = 100000
max_epochs = 0
max_steps = 100000
eval_frequency = 2000
# Other settings
seed = 0
accumulate_gradient = 1
use_pytorch_for_gpu_memory = false
# Control how scores are printed and checkpoints are evaluated.
scores = ["speed", "ents_p", "ents_r", "ents_f"]
score_weights = {"ents_f": 1.0}
# These settings are invalid for the transformer models.
init_tok2vec = null
discard_oversize = false
omit_extra_lookups = false
[training.batch_size]
@schedules = "compounding.v1"
start = 100
stop = 2000
compound = 1.001
[training.optimizer]
@optimizers = "Adam.v1"
beta1 = 0.9
beta2 = 0.999
L2_is_weight_decay = true
L2 = 0.0
grad_clip = 1.0
use_averages = true
eps = 1e-8
learn_rate = 0.001
#[training.optimizer.learn_rate]
#@schedules = "warmup_linear.v1"
#warmup_steps = 1000
#total_steps = 50000
#initial_rate = 0.003
[nlp]
lang = "en"
vectors = null
[nlp.pipeline.ner]
factory = "ner"
learn_tokens = false
min_action_freq = 1
[nlp.pipeline.ner.model]
@architectures = "spacy.TransitionBasedParser.v1"
nr_feature_tokens = 3
hidden_width = 64
maxout_pieces = 2
use_upper = false
[nlp.pipeline.ner.model.tok2vec]
@architectures = "spacy.HashEmbedCNN.v1"
pretrained_vectors = ${nlp:vectors}
width = 300
depth = 4
window_size = 1
embed_size = 7000
maxout_pieces = 1
subword_features = true
dropout = ${training:dropout}