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

[system]
seed = 0
gpu_allocator = null

[nlp]
lang = "en"
pipeline = ["transformer","textcat"]
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
batch_size = 1000

[components]

[components.textcat]
factory = "textcat_multilabel"
threshold = 0.5

[components.textcat.model]
@architectures = "spacy.TextCatCNN.v1"
exclusive_classes = false
nO = null

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

[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.v1"
name = "xlm-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}
gold_preproc = ${corpora.train.gold_preproc}
max_length = ${corpora.train.max_length}
limit = 0
augmenter = null

[corpora.train]
@readers = "spacy.Corpus.v1"
path = ${paths:train}
gold_preproc = false
max_length = 500
limit = 0
augmenter = null

[training]
train_corpus = "corpora.train"
dev_corpus = "corpora.dev"
seed = ${system.seed}
gpu_allocator = ${system.gpu_allocator}
patience = 5000
eval_frequency = 400
dropout = 0.1
max_epochs = 10
max_steps = 0
accumulate_gradient = 3
frozen_components = []
before_to_disk = null

[training.batcher]
@batchers = "spacy.batch_by_sequence.v1"
size = 128
get_length = null

[training.logger]
@loggers = "spacy.ConsoleLogger.v1"
progress_bar = false

[training.optimizer]
@optimizers = "Adam.v1"
beta1 = 0.9
beta2 = 0.999
eps = 0.00000001
L2_is_weight_decay = true
L2 = 0.01
grad_clip = 1.0
use_averages = false

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

[training.score_weights]
cats_score = 0.5
cats_score_desc = null
cats_micro_p = null
cats_micro_r = null
cats_micro_f = null
cats_macro_p = null
cats_macro_r = null
cats_macro_f = 0.5
cats_macro_auc = null
cats_f_per_type = null
cats_macro_auc_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]