JanetBackEnd/EntityExtraction/base_config.cfg

83 lines
1.6 KiB
INI

# This is an auto-generated partial config. To use it with 'spacy train'
# you can run spacy init fill-config to auto-fill all default settings:
# python -m spacy init fill-config ./base_config.cfg ./config.cfg
[paths]
train = null
dev = null
vectors = null
[system]
gpu_allocator = "pytorch"
[nlp]
lang = "en"
pipeline = ["transformer","ner"]
batch_size = 128
[components]
[components.transformer]
factory = "transformer"
[components.transformer.model]
@architectures = "spacy-transformers.TransformerModel.v3"
name = "roberta-base"
tokenizer_config = {"use_fast": true}
[components.transformer.model.get_spans]
@span_getters = "spacy-transformers.strided_spans.v1"
window = 128
stride = 96
[components.ner]
factory = "ner"
[components.ner.model]
@architectures = "spacy.TransitionBasedParser.v2"
state_type = "ner"
extra_state_tokens = false
hidden_width = 64
maxout_pieces = 2
use_upper = false
nO = null
[components.ner.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0
[components.ner.model.tok2vec.pooling]
@layers = "reduce_mean.v1"
[corpora]
[corpora.train]
@readers = "spacy.Corpus.v1"
path = ${paths.train}
max_length = 0
[corpora.dev]
@readers = "spacy.Corpus.v1"
path = ${paths.dev}
max_length = 0
[training]
accumulate_gradient = 3
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
[training.optimizer]
@optimizers = "Adam.v1"
[training.optimizer.learn_rate]
@schedules = "warmup_linear.v1"
warmup_steps = 250
total_steps = 20000
initial_rate = 5e-5
[training.batcher]
@batchers = "spacy.batch_by_padded.v1"
discard_oversize = true
size = 2000
buffer = 256
[initialize]
vectors = ${paths.vectors}