spaCy/examples/experiments/tok2vec-ner/multihashembed_tok2vec.cfg
Matthew Honnibal 333b1a308b
Adapt parser and NER for transformers (#5449)
* Draft layer for BILUO actions

* Fixes to biluo layer

* WIP on BILUO layer

* Add tests for BILUO layer

* Format

* Fix transitions

* Update test

* Link in the simple_ner

* Update BILUO tagger

* Update __init__

* Import simple_ner

* Update test

* Import

* Add files

* Add config

* Fix label passing for BILUO and tagger

* Fix label handling for simple_ner component

* Update simple NER test

* Update config

* Hack train script

* Update BILUO layer

* Fix SimpleNER component

* Update train_from_config

* Add biluo_to_iob helper

* Add IOB layer

* Add IOBTagger model

* Update biluo layer

* Update SimpleNER tagger

* Update BILUO

* Read random seed in train-from-config

* Update use of normal_init

* Fix normalization of gradient in SimpleNER

* Update IOBTagger

* Remove print

* Tweak masking in BILUO

* Add dropout in SimpleNER

* Update thinc

* Tidy up simple_ner

* Fix biluo model

* Unhack train-from-config

* Update setup.cfg and requirements

* Add tb_framework.py for parser model

* Try to avoid memory leak in BILUO

* Move ParserModel into spacy.ml, avoid need for subclass.

* Use updated parser model

* Remove incorrect call to model.initializre in PrecomputableAffine

* Update parser model

* Avoid divide by zero in tagger

* Add extra dropout layer in tagger

* Refine minibatch_by_words function to avoid oom

* Fix parser model after refactor

* Try to avoid div-by-zero in SimpleNER

* Fix infinite loop in minibatch_by_words

* Use SequenceCategoricalCrossentropy in Tagger

* Fix parser model when hidden layer

* Remove extra dropout from tagger

* Add extra nan check in tagger

* Fix thinc version

* Update tests and imports

* Fix test

* Update test

* Update tests

* Fix tests

* Fix test

Co-authored-by: Ines Montani <ines@ines.io>
2020-05-18 22:23:33 +02:00

45 lines
736 B
INI

[training]
use_gpu = -1
limit = 0
dropout = 0.2
patience = 10000
eval_frequency = 200
scores = ["ents_p", "ents_r", "ents_f"]
score_weights = {"ents_f": 1}
orth_variant_level = 0.0
gold_preproc = true
max_length = 0
[training.batch_size]
@schedules = "compounding.v1"
start = 3000
stop = 3000
compound = 1.001
[optimizer]
@optimizers = "Adam.v1"
learn_rate = 0.001
beta1 = 0.9
beta2 = 0.999
[nlp]
lang = "en"
vectors = null
[nlp.pipeline.ner]
factory = "simple_ner"
[nlp.pipeline.ner.model]
@architectures = "spacy.BiluoTagger.v1"
[nlp.pipeline.ner.model.tok2vec]
@architectures = "spacy.HashEmbedCNN.v1"
width = 128
depth = 4
embed_size = 7000
maxout_pieces = 3
window_size = 1
subword_features = true
pretrained_vectors = null