hu_core_kbc_trf / config.cfg
oroszgy's picture
Update spacy pipeline to 3.5.2
81b9a58
[paths]
tagger_model = "models/hu_core_kbc_trf-tagger-3.5.2/model-best"
parser_model = "models/hu_core_kbc_trf-parser-3.5.2/model-best"
ner_model = "models/hu_core_kbc_trf-ner-3.5.2/model-best"
lemmatizer_lookups = "models/hu_core_kbc_trf-lookup-lemmatizer-3.5.2"
train = null
dev = null
vectors = null
init_tok2vec = null
[system]
seed = 0
gpu_allocator = null
[nlp]
lang = "hu"
pipeline = ["transformer","senter","tagger","morphologizer","lookup_lemmatizer","trainable_lemmatizer","parser","ner"]
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
batch_size = 1000
[components]
[components.lookup_lemmatizer]
factory = "hu.lookup_lemmatizer"
scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
source = ${paths.lemmatizer_lookups}
[components.morphologizer]
factory = "morphologizer"
extend = false
overwrite = true
scorer = {"@scorers":"spacy.morphologizer_scorer.v1"}
[components.morphologizer.model]
@architectures = "spacy.Tagger.v1"
nO = null
[components.morphologizer.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0
pooling = {"@layers":"reduce_mean.v1"}
upstream = "*"
[components.ner]
factory = "beam_ner"
beam_density = 0.01
beam_update_prob = 1
beam_width = 32
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 = true
hidden_width = 64
maxout_pieces = 3
use_upper = false
nO = null
[components.ner.model.tok2vec]
@architectures = "spacy-transformers.Tok2VecTransformer.v3"
name = "SZTAKI-HLT/hubert-base-cc"
mixed_precision = false
pooling = {"@layers":"reduce_mean.v1"}
grad_factor = 1.0
[components.ner.model.tok2vec.get_spans]
@span_getters = "spacy-transformers.strided_spans.v1"
window = 128
stride = 96
[components.ner.model.tok2vec.grad_scaler_config]
[components.ner.model.tok2vec.tokenizer_config]
use_fast = true
model_max_length = 512
[components.ner.model.tok2vec.transformer_config]
[components.parser]
factory = "parser"
learn_tokens = false
min_action_freq = 30
moves = null
scorer = {"@scorers":"spacy.parser_scorer.v1"}
update_with_oracle_cut_size = 100
[components.parser.model]
@architectures = "spacy.TransitionBasedParser.v2"
state_type = "parser"
extra_state_tokens = false
hidden_width = 128
maxout_pieces = 3
use_upper = false
nO = null
[components.parser.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0
pooling = {"@layers":"reduce_mean.v1"}
upstream = "*"
[components.senter]
factory = "senter"
overwrite = false
scorer = {"@scorers":"spacy.senter_scorer.v1"}
[components.senter.model]
@architectures = "spacy.Tagger.v1"
nO = null
[components.senter.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0
upstream = "transformer"
pooling = {"@layers":"reduce_mean.v1"}
[components.tagger]
factory = "tagger"
neg_prefix = "!"
overwrite = false
scorer = {"@scorers":"spacy.tagger_scorer.v1"}
[components.tagger.model]
@architectures = "spacy.Tagger.v1"
nO = null
[components.tagger.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0
pooling = {"@layers":"reduce_mean.v1"}
upstream = "*"
[components.trainable_lemmatizer]
factory = "trainable_lemmatizer_v2"
backoff = "orth"
min_tree_freq = 1
overwrite = false
overwrite_labels = true
scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
top_k = 3
[components.trainable_lemmatizer.model]
@architectures = "spacy.Tagger.v1"
nO = null
[components.trainable_lemmatizer.model.tok2vec]
@architectures = "spacy-transformers.Tok2VecTransformer.v3"
name = "SZTAKI-HLT/hubert-base-cc"
mixed_precision = false
pooling = {"@layers":"reduce_mean.v1"}
grad_factor = 1.0
[components.trainable_lemmatizer.model.tok2vec.get_spans]
@span_getters = "spacy-transformers.strided_spans.v1"
window = 128
stride = 96
[components.trainable_lemmatizer.model.tok2vec.grad_scaler_config]
[components.trainable_lemmatizer.model.tok2vec.tokenizer_config]
use_fast = true
model_max_length = 512
[components.trainable_lemmatizer.model.tok2vec.transformer_config]
[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 = "SZTAKI-HLT/hubert-base-cc"
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
model_max_length = 512
[components.transformer.model.transformer_config]
[corpora]
[corpora.dev]
@readers = "spacy.Corpus.v1"
path = ${paths.dev}
gold_preproc = false
max_length = 0
limit = 0
augmenter = null
[corpora.train]
@readers = "spacy.Corpus.v1"
path = ${paths.train}
gold_preproc = false
max_length = 0
limit = 0
augmenter = null
[training]
seed = ${system.seed}
gpu_allocator = ${system.gpu_allocator}
dropout = 0.1
accumulate_gradient = 1
patience = 1600
max_epochs = 0
max_steps = 20000
eval_frequency = 200
frozen_components = []
annotating_components = []
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
before_to_disk = null
before_update = null
[training.batcher]
@batchers = "spacy.batch_by_words.v1"
discard_oversize = false
tolerance = 0.2
get_length = null
[training.batcher.size]
@schedules = "compounding.v1"
start = 100
stop = 1000
compound = 1.001
t = 0.0
[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
learn_rate = 0.001
[training.score_weights]
sents_f = 0.0
sents_p = null
sents_r = null
tag_acc = 0.2
pos_acc = 0.1
morph_acc = 0.1
morph_per_feat = null
lemma_acc = 0.2
dep_uas = 0.1
dep_las = 0.1
dep_las_per_type = null
ents_f = 0.2
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]