training_trf/model-best/config.cfg

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

[system]
seed = 342
gpu_allocator = "pytorch"

[nlp]
lang = "en"
pipeline = ["transformer","torch_ner"]
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
batch_size = 8

[components]

[components.torch_ner]
factory = "torch_ner"

[components.torch_ner.model]
@architectures = "TorchEntityRecognizer.v1"
hidden_width = 48
nO = 11
width = 768
dropout = 0.1

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

[components.transformer]
factory = "transformer"
max_batch_items = 1024
set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}

[components.transformer.model]
@architectures = "spacy-transformers.TransformerModel.v1"
name = "roberta-base"

[components.transformer.model.get_spans]
@span_getters = "spacy-transformers.strided_spans.v1"
window = 128
stride = 96

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

[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]
seed = ${system.seed}
gpu_allocator = ${system.gpu_allocator}
dropout = 0.1
accumulate_gradient = 1
patience = 1600000
max_epochs = 0
max_steps = 20000
eval_frequency = 100
frozen_components = []
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
before_to_disk = null
annotating_components = []

[training.batcher]
@batchers = "spacy.batch_by_padded.v1"
discard_oversize = true
size = 100
buffer = 256
get_length = null

[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

[training.optimizer.learn_rate]
@schedules = "warmup_linear.v1"
warmup_steps = 250
total_steps = 20000
initial_rate = 0.00005

[training.score_weights]
ents_f = 1.0
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]