da_dacy_small_trf / config.cfg
KennethEnevoldsen's picture
Updated to version v0.2.0
0eadea0
[paths]
train = null
dev = null
init_tok2vec = null
vectors = null
model_source = "training/da_dacy_small_trf2/model-last"
[system]
gpu_allocator = "pytorch"
seed = 0
[nlp]
lang = "da"
pipeline = ["transformer","tagger","morphologizer","trainable_lemmatizer","parser","ner","coref","span_resolver","span_cleaner","entity_linker"]
batch_size = 512
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
[components]
[components.coref]
factory = "experimental_coref"
span_cluster_prefix = "coref_head_clusters"
[components.coref.model]
@architectures = "spacy-experimental.Coref.v1"
distance_embedding_size = 20
dropout = 0.3
hidden_size = 1024
depth = 2
antecedent_limit = 100
antecedent_batch_size = 512
[components.coref.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 0.5
upstream = "transformer"
pooling = {"@layers":"reduce_mean.v1"}
[components.coref.scorer]
@scorers = "spacy-experimental.coref_scorer.v1"
span_cluster_prefix = "coref_head_clusters"
[components.entity_linker]
factory = "entity_linker"
candidates_batch_size = 1
entity_vector_length = 768
generate_empty_kb = {"@misc":"spacy.EmptyKB.v2"}
get_candidates = {"@misc":"spacy.CandidateGenerator.v1"}
get_candidates_batch = {"@misc":"spacy.CandidateBatchGenerator.v1"}
incl_context = true
incl_prior = true
labels_discard = []
n_sents = 0
overwrite = true
scorer = {"@scorers":"spacy.entity_linker_scorer.v1"}
threshold = null
use_gold_ents = true
[components.entity_linker.model]
@architectures = "spacy.EntityLinker.v2"
nO = null
[components.entity_linker.model.tok2vec]
@architectures = "spacy.HashEmbedCNN.v2"
pretrained_vectors = null
width = 96
depth = 2
embed_size = 2000
window_size = 1
maxout_pieces = 3
subword_features = true
[components.morphologizer]
factory = "morphologizer"
extend = false
overwrite = true
scorer = {"@scorers":"spacy.morphologizer_scorer.v1"}
[components.morphologizer.model]
@architectures = "spacy.Tagger.v2"
nO = null
normalize = false
[components.morphologizer.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0
pooling = {"@layers":"reduce_mean.v1"}
upstream = "transformer"
[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 = "transformer"
[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 = "transformer"
[components.span_cleaner]
factory = "experimental_span_cleaner"
prefix = "coref_head_clusters"
[components.span_resolver]
factory = "experimental_span_resolver"
input_prefix = "coref_head_clusters"
output_prefix = "coref_clusters"
[components.span_resolver.model]
@architectures = "spacy-experimental.SpanResolver.v1"
hidden_size = 1024
distance_embedding_size = 64
conv_channels = 4
window_size = 1
max_distance = 128
prefix = "coref_head_clusters"
[components.span_resolver.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 0.0
upstream = "transformer"
pooling = {"@layers":"reduce_mean.v1"}
[components.span_resolver.scorer]
@scorers = "spacy-experimental.span_resolver_scorer.v1"
input_prefix = "coref_head_clusters"
output_prefix = "coref_clusters"
[components.tagger]
factory = "tagger"
neg_prefix = "!"
overwrite = false
scorer = {"@scorers":"spacy.tagger_scorer.v1"}
[components.tagger.model]
@architectures = "spacy.Tagger.v2"
nO = null
normalize = false
[components.tagger.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0
pooling = {"@layers":"reduce_mean.v1"}
upstream = "transformer"
[components.trainable_lemmatizer]
factory = "trainable_lemmatizer"
backoff = "orth"
min_tree_freq = 3
overwrite = false
scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
top_k = 1
[components.trainable_lemmatizer.model]
@architectures = "spacy.Tagger.v2"
nO = null
normalize = false
[components.trainable_lemmatizer.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0
pooling = {"@layers":"reduce_mean.v1"}
upstream = "transformer"
[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 = "jonfd/electra-small-nordic"
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}
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]
tag_acc = 0.12
pos_acc = 0.06
morph_acc = 0.06
morph_per_feat = null
lemma_acc = 0.12
dep_uas = 0.06
dep_las = 0.06
dep_las_per_type = null
sents_p = null
sents_r = null
sents_f = 0.0
ents_f = 0.12
ents_p = 0.0
ents_r = 0.0
ents_per_type = null
coref_f = 0.12
coref_p = null
coref_r = null
span_accuracy = 0.12
nel_micro_f = 0.12
nel_micro_r = null
nel_micro_p = 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]