config.cfg

[paths]
train = "data/engagement_three_train5.spacy"
dev = "data/engagement_three_dev5.spacy"
vectors = null
init_tok2vec = null

[system]
gpu_allocator = "pytorch"
seed = 0

[nlp]
lang = "en"
pipeline = ["transformer","parser","tagger","ner","attribute_ruler","lemmatizer","trainable_transformer","spancat"]
batch_size = 10
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}

[components]

[components.attribute_ruler]
factory = "attribute_ruler"
scorer = {"@scorers":"spacy.attribute_ruler_scorer.v1"}
validate = false

[components.lemmatizer]
factory = "lemmatizer"
mode = "rule"
model = null
overwrite = false
scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}

[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
upstream = "transformer"
pooling = {"@layers":"reduce_mean.v1"}

[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 = 64
maxout_pieces = 2
use_upper = false
nO = null

[components.parser.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0
upstream = "transformer"
pooling = {"@layers":"reduce_mean.v1"}

[components.spancat]
factory = "spancat"
max_positive = null
scorer = {"@scorers":"spacy.spancat_scorer.v1"}
spans_key = ${vars.spans_key}
threshold = 0.5

[components.spancat.model]
@architectures = "Ensemble_SpanCategorizer.v2"
LSTMhidden = 200
LSTMdepth = 1
LSTMdropout = 0.0

[components.spancat.model.reducer1]
@layers = "Mish_two_way_reducer.v2"
depth = 2
dropout = 0.2
hidden_size = 256

[components.spancat.model.reducer2]
@layers = "Mish_mean_max_reducer.v1"
depth = 1
dropout = 0.4
hidden_size = 128

[components.spancat.model.scorer]
@layers = "spacy.LinearLogistic.v1"
nO = null
nI = null

[components.spancat.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0
pooling = {"@layers":"reduce_mean.v1"}
upstream = "trainable_transformer"

[components.spancat.model.tok2vec_trf]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 0
pooling = {"@layers":"reduce_mean.v1"}
upstream = "transformer"

[components.spancat.suggester]
@misc = "spacy-experimental.ngram_subtree_suggester.v1"
sizes = [1,2,3,4,5,6,7,8,9,10,11,12]

[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
upstream = "transformer"
pooling = {"@layers":"reduce_mean.v1"}

[components.trainable_transformer]
factory = "transformer"
max_batch_items = 4096
set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}

[components.trainable_transformer.model]
name = "egumasa/roberta-base-academic3"
@architectures = "spacy-transformers.TransformerModel.v1"

[components.trainable_transformer.model.get_spans]
@span_getters = "spacy-transformers.strided_spans.v1"
window = 384
stride = 288

[components.trainable_transformer.model.tokenizer_config]
use_fast = true

[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"
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 = 2000
gold_preproc = false
limit = 0
augmenter = null

[training]
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
seed = ${system.seed}
gpu_allocator = ${system.gpu_allocator}
dropout = 0.1
accumulate_gradient = 4
patience = 3000
max_epochs = 0
max_steps = 20000
eval_frequency = 200
frozen_components = ["transformer","parser","tagger","ner","attribute_ruler","lemmatizer"]
annotating_components = ["transformer","parser"]
before_to_disk = null

[training.batcher]
@batchers = "spacy.batch_by_words.v1"
discard_oversize = false
tolerance = 0.2
get_length = null

[training.batcher.size]
start = 500
@schedules = "compounding.v1"
stop = 1000
compound = 1.0002
t = 0.0

[training.logger]
@loggers = "spacy.WandbLogger.v4"
project_name = "Spancat_5-fold"
remove_config_values = ["paths.train","paths.dev","corpora.train.path","corpora.dev.path"]
model_log_interval = null
entity = "e-masaki0101"
log_dataset_dir = null
run_name = null
log_best_dir = null
log_latest_dir = null

[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]
initial_rate = 0.0000565344
@schedules = "warmup_linear.v1"
warmup_steps = 1000
total_steps = 20000

[training.score_weights]
dep_uas = null
dep_las = null
dep_las_per_type = null
sents_p = null
sents_r = null
sents_f = null
tag_acc = null
ents_f = null
ents_p = null
ents_r = null
ents_per_type = null
lemma_acc = null
spans_sc_f = 0.5
spans_sc_p = 0.0
spans_sc_r = 0.5

[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]

[vars]
spans_key = "sc"