spaCy/spacy/cli/templates/quickstart_training.jinja

{# This is a template for training configs used for the quickstart widget in
the docs and the init config command. It encodes various best practices and
can help generate the best possible configuration, given a user's requirements. #}
# This is an auto-generated config for training a model with 'spacy train'
[paths]
train = ""
dev = ""

[nlp]
lang = "{{ lang }}"
pipeline = {{ pipeline|safe }}
tokenizer = {"@tokenizers": "spacy.Tokenizer.v1"}

[components]

{# TRANSFORMER PIPELINE #}
{%- if has_transformer -%}
[components.transformer]
factory = "transformer"

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

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

{% if "tagger" in components %}
[components.tagger]
factory = "tagger"

[components.tagger.model]
@architectures = "spacy.Tagger.v1"
nO = null

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

[components.tagger.model.tok2vec.pooling]
@layers = "reduce_mean.v1"
{%- endif %}

{% if "parser" in components -%}
[components.parser]
factory = "parser"

[components.parser.model]
@architectures = "spacy.TransitionBasedParser.v1"
nr_feature_tokens = 8
hidden_width = 128
maxout_pieces = 3
use_upper = false
nO = null

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

[components.parser.model.tok2vec.pooling]
@layers = "reduce_mean.v1"
{%- endif %}

{% if "ner" in components -%}
[components.ner]
factory = "ner"

[components.ner.model]
@architectures = "spacy.TransitionBasedParser.v1"
nr_feature_tokens = 3
hidden_width = 64
maxout_pieces = 2
use_upper = false
nO = null

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

[components.ner.model.tok2vec.pooling]
@layers = "reduce_mean.v1"
{% endif -%}

{# NON-TRANSFORMER PIPELINE #}
{% else -%}

{%- if hardware == "gpu" -%}
# There are no recommended transformer weights available for language '{{ lang }}'
# yet, so the pipeline described here is not transformer-based.
{%- endif %}

[components.tok2vec]
factory = "tok2vec"

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

[components.tok2vec.model.embed]
@architectures = "spacy.MultiHashEmbed.v1"
width = ${components.tok2vec.model.encode:width}
rows = {{ 2000 if optimize == "efficiency" else 7000 }}
also_embed_subwords = {{ true if has_letters else false }}
also_use_static_vectors = {{ true if optimize == "accuracy" else false }}

[components.tok2vec.model.encode]
@architectures = "spacy.MaxoutWindowEncoder.v1"
width = {{ 96 if optimize == "efficiency" else 256 }}
depth = {{ 4 if optimize == "efficiency" else 8 }}
window_size = 1
maxout_pieces = 3

{% if "tagger" in components %}
[components.tagger]
factory = "tagger"

[components.tagger.model]
@architectures = "spacy.Tagger.v1"
nO = null

[components.tagger.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = ${components.tok2vec.model.encode:width}
{%- endif %}

{% if "parser" in components -%}
[components.parser]
factory = "parser"

[components.parser.model]
@architectures = "spacy.TransitionBasedParser.v1"
nr_feature_tokens = 8
hidden_width = 128
maxout_pieces = 3
use_upper = true
nO = null

[components.parser.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = ${components.tok2vec.model.encode:width}
{%- endif %}

{% if "ner" in components %}
[components.ner]
factory = "ner"

[components.ner.model]
@architectures = "spacy.TransitionBasedParser.v1"
nr_feature_tokens = 6
hidden_width = 64
maxout_pieces = 2
use_upper = true
nO = null

[components.ner.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = ${components.tok2vec.model.encode:width}
{% endif %}
{% endif %}

{% for pipe in components %}
{% if pipe not in ["tagger", "parser", "ner"] %}
{# Other components defined by the user: we just assume they're factories #}
[components.{{ pipe }}]
factory = "{{ pipe }}"
{% endif %}
{% endfor %}

[training]
vectors = {{ ('"en_vectors_web_lg"' if optimize == "accuracy" and not has_transformer else false)|safe }}

{% if has_transformer -%}
{#- accumulate_gradient = {{ transformer_info["size_factor"] }} #}
accumulate_gradient = 3
{% endif -%}

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

[training.optimizer.learn_rate]
@schedules = "warmup_linear.v1"
warmup_steps = 250
total_steps = 20000
initial_rate = 5e-5

[training.train_corpus]
@readers = "spacy.Corpus.v1"
path = ${paths:train}
max_length = {{ 500 if hardware == "gpu" else 0 }}

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

{% if has_transformer %}
[training.batcher]
@batchers = "batch_by_padded.v1"
discard_oversize = true
size = 2000
buffer = 256
{%- else %}
[training.batcher]
@batchers = "batch_by_words.v1"
discard_oversize = false
tolerance = 0.2

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

[training.score_weights]
{%- if "tagger" in components %}
tag_acc = {{ (1.0 / components|length)|round(2) }}
{%- endif -%}
{%- if "parser" in components %}
dep_uas = 0.0
dep_las = {{ (1.0 / components|length)|round(2) }}
sents_f = 0.0
{%- endif %}
{%- if "ner" in components %}
ents_f = {{ (1.0 / components|length)|round(2) }}
ents_p = 0.0
ents_r = 0.0
{%- endif -%}