configs/sc_TL_trf.cfg

[paths]
train = "./scdata/train.spacy"
dev = "./scdata/dev.spacy"
vectors = null
init_tok2vec = null

[system]
gpu_allocator = null
seed = 0

[nlp]
lang = "en"
pipeline = ["transformer","spancat"]
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
batch_size = 64
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}

[components]

[components.spancat]
source = "./chemrelmodels/sc/trf"
component = "spancat"

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

[components.spancat.model.reducer]
@layers = "spacy.mean_max_reducer.v1"
hidden_size = 128

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

[components.spancat.model.tok2vec]
@architectures = "spacy.Tok2Vec.v1"

[components.spancat.model.tok2vec.embed]
@architectures = "spacy.MultiHashEmbed.v1"
width = 96
rows = [5000,2000,1000,1000]
attrs = ["ORTH","PREFIX","SUFFIX","SHAPE"]
include_static_vectors = false

[components.spancat.model.tok2vec.encode]
@architectures = "spacy.MaxoutWindowEncoder.v1"
width = 96
window_size = 10
maxout_pieces = 3
depth = 4

[components.spancat.suggester]
@misc = "spacy.ngram_range_suggester.v1"
min_size = 1
max_size = 44

[components.transformer]
source = "./chemrelmodels/sc/trf"
component = "transformer"

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

[training]
train_corpus = "corpora.train"
dev_corpus = "corpora.dev"
seed = ${system:seed}
gpu_allocator = ${system:gpu_allocator}
dropout = 0.1
accumulate_gradient = 3
patience = 500000000
max_epochs = 0
max_steps = 20000
eval_frequency = 1
before_to_disk = null
frozen_components = []
annotating_components = []

[training.batcher]
@batchers = "spacy.batch_by_padded.v1"
discard_oversize = true
get_length = null
size = 1024
buffer = 256

[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 = true
eps = 0.00000001

[training.optimizer.learn_rate]
@schedules = "warmup_linear.v1"
warmup_steps = 0
total_steps = 20000
initial_rate = 0.0001

[training.score_weights]
spans_sc_f = 1.0
spans_sc_p = 0.0
spans_sc_r = 0.0

[pretraining]

[initialize]
vectors = ${paths.vectors}
init_tok2vec = ${paths.init_tok2vec}
vocab_data = null
lookups = null
before_init = null
after_init = null

[initialize.components]

[initialize.components.spancat]

[initialize.components.spancat.labels]
@readers = "spacy.read_labels.v1"
path = "labels/spancat.json"
require = false

[initialize.tokenizer]