mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 13:47:13 +03:00
c0f4a1e43b
* verbose and tag_map options * adding init_tok2vec option and only changing the tok2vec that is specified * adding omit_extra_lookups and verifying textcat config * wip * pretrain bugfix * add replace and resume options * train_textcat fix * raw text functionality * improve UX when KeyError or when input data can't be parsed * avoid unnecessary access to goldparse in TextCat pipe * save performance information in nlp.meta * add noise_level to config * move nn_parser's defaults to config file * multitask in config - doesn't work yet * scorer offering both F and AUC options, need to be specified in config * add textcat verification code from old train script * small fixes to config files * clean up * set default config for ner/parser to allow create_pipe to work as before * two more test fixes * small fixes * cleanup * fix NER pickling + additional unit test * create_pipe as before
76 lines
1.4 KiB
INI
76 lines
1.4 KiB
INI
[training]
|
|
patience = 10000
|
|
eval_frequency = 200
|
|
dropout = 0.2
|
|
init_tok2vec = null
|
|
vectors = null
|
|
max_epochs = 100
|
|
orth_variant_level = 0.0
|
|
noise_level = 0.0
|
|
gold_preproc = true
|
|
max_length = 0
|
|
use_gpu = -1
|
|
scores = ["tags_acc", "uas", "las"]
|
|
score_weights = {"las": 0.8, "tags_acc": 0.2}
|
|
limit = 0
|
|
seed = 0
|
|
accumulate_gradient = 2
|
|
discard_oversize = false
|
|
|
|
[training.batch_size]
|
|
@schedules = "compounding.v1"
|
|
start = 100
|
|
stop = 1000
|
|
compound = 1.001
|
|
|
|
[training.optimizer]
|
|
@optimizers = "Adam.v1"
|
|
learn_rate = 0.001
|
|
beta1 = 0.9
|
|
beta2 = 0.999
|
|
|
|
[nlp]
|
|
lang = "en"
|
|
vectors = ${training:vectors}
|
|
|
|
[nlp.pipeline.tok2vec]
|
|
factory = "tok2vec"
|
|
|
|
[nlp.pipeline.tagger]
|
|
factory = "tagger"
|
|
|
|
[nlp.pipeline.parser]
|
|
factory = "parser"
|
|
learn_tokens = false
|
|
min_action_freq = 1
|
|
beam_width = 1
|
|
beam_update_prob = 1.0
|
|
|
|
[nlp.pipeline.tagger.model]
|
|
@architectures = "spacy.Tagger.v1"
|
|
|
|
[nlp.pipeline.tagger.model.tok2vec]
|
|
@architectures = "spacy.Tok2VecTensors.v1"
|
|
width = ${nlp.pipeline.tok2vec.model:width}
|
|
|
|
[nlp.pipeline.parser.model]
|
|
@architectures = "spacy.TransitionBasedParser.v1"
|
|
nr_feature_tokens = 8
|
|
hidden_width = 64
|
|
maxout_pieces = 3
|
|
|
|
[nlp.pipeline.parser.model.tok2vec]
|
|
@architectures = "spacy.Tok2VecTensors.v1"
|
|
width = ${nlp.pipeline.tok2vec.model:width}
|
|
|
|
[nlp.pipeline.tok2vec.model]
|
|
@architectures = "spacy.HashEmbedCNN.v1"
|
|
pretrained_vectors = ${nlp:vectors}
|
|
width = 96
|
|
depth = 4
|
|
window_size = 1
|
|
embed_size = 2000
|
|
maxout_pieces = 3
|
|
subword_features = true
|
|
dropout = null
|