[paths]
train = "data/engagement_spl_train.spacy"
dev = "data/engagement_spl_dev.spacy"
vectors = null
init_tok2vec = null
source = "en_core_web_trf"

[system]
gpu_allocator = "pytorch"
seed = 0

[nlp]
lang = "en"
pipeline = ["transformer","tagger","parser","ner","trainable_transformer","span_finder","spancat"]
batch_size = 16
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}

[components]

[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.span_finder]
factory = "experimental_span_finder"
max_length = 0
min_length = 0
predicted_key = "span_candidates"
threshold = 0.2
training_key = ${vars.spans_key}

[components.span_finder.model]
@architectures = "spacy-experimental.SpanFinder.v1"

[components.span_finder.model.scorer]
@layers = "spacy.LinearLogistic.v1"
nO = 2
nI = null

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

[components.span_finder.scorer]
@scorers = "spacy-experimental.span_finder_scorer.v1"
predicted_key = ${components.span_finder.predicted_key}
training_key = ${vars.spans_key}

[components.spancat]
factory = "spancat"
max_positive = 2
scorer = {"@scorers":"spacy.spancat_scorer.v1"}
spans_key = ${vars.spans_key}
threshold = 0.5

[components.spancat.model]
@architectures = "spacy.SpanCategorizer.v1"

[components.spancat.model.reducer]
@layers = "mean_max_reducer.v1.5"
hidden_size = 128
dropout = 0.2

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

[components.spancat.suggester]
@misc = "spacy-experimental.span_finder_suggester.v1"
candidates_key = ${components.span_finder.predicted_key}

[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]
@architectures = "spacy-transformers.TransformerModel.v1"
name = "egumasa/roberta-base-finetuned-academic"

[components.trainable_transformer.model.get_spans]
@span_getters = "spacy-transformers.strided_spans.v1"
window = 196
stride = 147

[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 = 1
patience = 2000
max_epochs = 0
max_steps = 20000
eval_frequency = 100
frozen_components = ["transformer","parser","tagger","ner"]
annotating_components = ["span_finder"]
before_to_disk = null

[training.batcher]
@batchers = "spacy.batch_by_words.v1"
discard_oversize = false
tolerance = 0.3
get_length = null

[training.batcher.size]
@schedules = "compounding.v1"
start = 200
stop = 500
compound = 1.0005
t = 0.0

[training.logger]
@loggers = "spacy.WandbLogger.v3"
project_name = "spnacat_engagementv2"
remove_config_values = ["paths.train","paths.dev","corpora.train.path","corpora.dev.path"]
model_log_interval = 100
entity = "e-masaki0101"
run_name = "OS_AdapR_max1-128do0.2_Cyc1000_RAdam_20221030"
log_dataset_dir = null

[training.optimizer]
@optimizers = "RAdam.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]
@schedules = "cyclic_triangular.v1"
min_lr = 0.00001
max_lr = 0.0001
period = 500

[training.score_weights]
tag_acc = null
dep_uas = null
dep_las = null
dep_las_per_type = null
sents_p = null
sents_r = null
sents_f = null
ents_f = null
ents_p = null
ents_r = null
ents_per_type = null
span_finder_span_candidates_f = 0.0
span_finder_span_candidates_p = 0.0
span_finder_span_candidates_r = 0.18
spans_sc_f = 0.64
spans_sc_p = 0.09
spans_sc_r = 0.09
lemma_acc = 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]

[vars]
spans_key = "sc"