149 lines
2.9 KiB
INI
149 lines
2.9 KiB
INI
[paths]
|
||
train = null
|
||
dev = null
|
||
vectors = null
|
||
init_tok2vec = null
|
||
|
||
[system]
|
||
gpu_allocator = "pytorch"
|
||
seed = 0
|
||
|
||
[nlp]
|
||
lang = "en"
|
||
pipeline = ["transformer","ner"]
|
||
batch_size = 128
|
||
disabled = []
|
||
before_creation = null
|
||
after_creation = null
|
||
after_pipeline_creation = null
|
||
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
|
||
vectors = {"@vectors":"spacy.Vectors.v1"}
|
||
|
||
[components]
|
||
|
||
[components.ner]
|
||
factory = "ner"
|
||
incorrect_spans_key = null
|
||
moves = null
|
||
scorer = {"@scorers":"spacy.ner_scorer.v1"}
|
||
update_with_oracle_cut_size = 100
|
||
|
||
[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
|
||
pooling = {"@layers":"reduce_mean.v1"}
|
||
upstream = "*"
|
||
|
||
[components.transformer]
|
||
factory = "transformer"
|
||
max_batch_items = 4096
|
||
set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}
|
||
|
||
[components.transformer.model]
|
||
@architectures = "spacy-transformers.TransformerModel.v3"
|
||
# name = "roberta-base"
|
||
# 若HuggingFace连接失败，则把模型文件下载到本地，并修改name
|
||
name = "../cache/roberta_base"
|
||
mixed_precision = false
|
||
|
||
[components.transformer.model.get_spans]
|
||
@span_getters = "spacy-transformers.strided_spans.v1"
|
||
window = 128
|
||
stride = 96
|
||
|
||
[components.transformer.model.grad_scaler_config]
|
||
|
||
[components.transformer.model.tokenizer_config]
|
||
use_fast = true
|
||
|
||
[components.transformer.model.transformer_config]
|
||
|
||
[corpora]
|
||
|
||
[corpora.dev]
|
||
@readers = "spacy.Corpus.v1"
|
||
path = ${paths.dev}
|
||
max_length = 0
|
||
gold_preproc = false
|
||
limit = 0
|
||
augmenter = null
|
||
|
||
[corpora.train]
|
||
@readers = "spacy.Corpus.v1"
|
||
path = ${paths.train}
|
||
max_length = 0
|
||
gold_preproc = false
|
||
limit = 0
|
||
augmenter = null
|
||
|
||
[training]
|
||
accumulate_gradient = 3
|
||
dev_corpus = "corpora.dev"
|
||
train_corpus = "corpora.train"
|
||
seed = ${system.seed}
|
||
gpu_allocator = ${system.gpu_allocator}
|
||
dropout = 0.1
|
||
patience = 1600
|
||
max_epochs = 0
|
||
max_steps = 20000
|
||
eval_frequency = 200
|
||
frozen_components = []
|
||
annotating_components = []
|
||
before_to_disk = null
|
||
before_update = null
|
||
|
||
[training.batcher]
|
||
@batchers = "spacy.batch_by_padded.v1"
|
||
discard_oversize = true
|
||
size = 2000
|
||
buffer = 256
|
||
get_length = null
|
||
|
||
[training.logger]
|
||
@loggers = "spacy.ConsoleLogger.v1"
|
||
progress_bar = false
|
||
|
||
[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 = 0.00000001
|
||
|
||
[training.optimizer.learn_rate]
|
||
@schedules = "warmup_linear.v1"
|
||
warmup_steps = 250
|
||
total_steps = 20000
|
||
initial_rate = 0.00005
|
||
|
||
[training.score_weights]
|
||
ents_f = 1.0
|
||
ents_p = 0.0
|
||
ents_r = 0.0
|
||
ents_per_type = null
|
||
|
||
[pretraining]
|
||
|
||
[initialize]
|
||
vectors = ${paths.vectors}
|
||
init_tok2vec = ${paths.init_tok2vec}
|
||
vocab_data = null
|
||
lookups = null
|
||
before_init = null
|
||
after_init = null
|
||
|
||
[initialize.components]
|
||
|
||
[initialize.tokenizer] |