base_config.cfg

# This is an auto-generated partial config. To use it with 'spacy train'
# you can run spacy init fill-config to auto-fill all default settings:
# python -m spacy init fill-config ./base_config.cfg ./config.cfg
[paths]
train = "./train.spacy"
dev = "./valid.spacy"
vectors = null
[system]
gpu_allocator = null

[nlp]
lang = "en"
pipeline = ["transformer", "textcat"]
batch_size = 32

[components]

[components.transformer]
factory = "transformer"

[components.transformer.model]
@architectures = "spacy-transformers.TransformerModel.v1"
name = "roberta-base"
tokenizer_config = {"use_fast" : true}

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

[components.textcat]
factory = "textcat"

[components.textcat.model]
# @architectures = "spacy.TextCatBOW.v2"
@architectures = "spacy.TextCatEnsemble.v2"
nO = null
# exclusive_classes = true
# ngram_size = 1
# no_output_layer = false

[components.textcat.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0

[components.textcat.model.tok2vec.pooling]
@layers = "reduce_mean.v1"

[corpora]

[corpora.train]
@readers = "spacy.Corpus.v1"
path = ${paths.train}
max_length = 0

[corpora.dev]
@readers = "spacy.Corpus.v1"
path = ${paths.dev}
max_length = 0

[training]
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"

[training.optimizer]
@optimizers = "Adam.v1"

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

[training.batcher.size]
@schedules = "compounding.v1"
start = 100
stop = 1000
compound = 1.001

[initialize]
vectors = ${paths.vectors}