mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-20 19:09:21 +03:00
0fe43f40f1
* Support registered vectors * Format * Auto-fill [nlp] on load from config and from bytes/disk * Only auto-fill [nlp] * Undo all changes to Language.from_disk * Expand BaseVectors These methods are needed in various places for training and vector similarity. * isort * More linting * Only fill [nlp.vectors] * Update spacy/vocab.pyx Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Revert changes to test related to auto-filling [nlp] * Add vectors registry * Rephrase error about vocab methods for vectors * Switch to dummy implementation for BaseVectors.to_ops * Add initial draft of docs * Remove example from BaseVectors docs * Apply suggestions from code review Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Update website/docs/api/basevectors.mdx Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> * Fix type and lint bpemb example * Update website/docs/api/basevectors.mdx --------- Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
141 lines
4.3 KiB
INI
141 lines
4.3 KiB
INI
[paths]
|
|
train = null
|
|
dev = null
|
|
vectors = null
|
|
init_tok2vec = null
|
|
|
|
[system]
|
|
seed = 0
|
|
gpu_allocator = null
|
|
|
|
[nlp]
|
|
lang = null
|
|
# List of pipeline component names, in order. The names should correspond to
|
|
# components defined in the [components block]
|
|
pipeline = []
|
|
# Components that are loaded but disabled by default
|
|
disabled = []
|
|
# Optional callbacks to modify the nlp object before it's initialized, after
|
|
# it's created and after the pipeline has been set up
|
|
before_creation = null
|
|
after_creation = null
|
|
after_pipeline_creation = null
|
|
# Default batch size to use with nlp.pipe and nlp.evaluate
|
|
batch_size = 1000
|
|
|
|
[nlp.tokenizer]
|
|
@tokenizers = "spacy.Tokenizer.v1"
|
|
|
|
[nlp.vectors]
|
|
@vectors = "spacy.Vectors.v1"
|
|
|
|
# The pipeline components and their models
|
|
[components]
|
|
|
|
# Readers for corpora like dev and train.
|
|
[corpora]
|
|
|
|
[corpora.train]
|
|
@readers = "spacy.Corpus.v1"
|
|
path = ${paths.train}
|
|
# Whether to train on sequences with 'gold standard' sentence boundaries
|
|
# and tokens. If you set this to true, take care to ensure your run-time
|
|
# data is passed in sentence-by-sentence via some prior preprocessing.
|
|
gold_preproc = false
|
|
# Limitations on training document length
|
|
max_length = 0
|
|
# Limitation on number of training examples
|
|
limit = 0
|
|
# Apply some simply data augmentation, where we replace tokens with variations.
|
|
# This is especially useful for punctuation and case replacement, to help
|
|
# generalize beyond corpora that don't/only have smart quotes etc.
|
|
augmenter = null
|
|
|
|
[corpora.dev]
|
|
@readers = "spacy.Corpus.v1"
|
|
path = ${paths.dev}
|
|
# Whether to train on sequences with 'gold standard' sentence boundaries
|
|
# and tokens. If you set this to true, take care to ensure your run-time
|
|
# data is passed in sentence-by-sentence via some prior preprocessing.
|
|
gold_preproc = false
|
|
# Limitations on training document length
|
|
max_length = 0
|
|
# Limitation on number of training examples
|
|
limit = 0
|
|
# Optional callback for data augmentation
|
|
augmenter = null
|
|
|
|
# Training hyper-parameters and additional features.
|
|
[training]
|
|
seed = ${system.seed}
|
|
gpu_allocator = ${system.gpu_allocator}
|
|
dropout = 0.1
|
|
accumulate_gradient = 1
|
|
# Controls early-stopping, i.e., the number of steps to continue without
|
|
# improvement before stopping. 0 disables early stopping.
|
|
patience = 1600
|
|
# Number of epochs. 0 means unlimited. If >= 0, train corpus is loaded once in
|
|
# memory and shuffled within the training loop. -1 means stream train corpus
|
|
# rather than loading in memory with no shuffling within the training loop.
|
|
max_epochs = 0
|
|
# Maximum number of update steps to train for. 0 means an unlimited number of steps.
|
|
max_steps = 20000
|
|
eval_frequency = 200
|
|
# Control how scores are printed and checkpoints are evaluated.
|
|
score_weights = {}
|
|
# Names of pipeline components that shouldn't be updated during training
|
|
frozen_components = []
|
|
# Names of pipeline components that should set annotations during training
|
|
annotating_components = []
|
|
# Location in the config where the dev corpus is defined
|
|
dev_corpus = "corpora.dev"
|
|
# Location in the config where the train corpus is defined
|
|
train_corpus = "corpora.train"
|
|
# Optional callback before nlp object is saved to disk after training
|
|
before_to_disk = null
|
|
# Optional callback that is invoked at the start of each training step
|
|
before_update = null
|
|
|
|
[training.logger]
|
|
@loggers = "spacy.ConsoleLogger.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
|
|
|
|
[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 = 1e-8
|
|
learn_rate = 0.001
|
|
|
|
# These settings are used when nlp.initialize() is called (typically before
|
|
# training or pretraining). Components and the tokenizer can each define their
|
|
# own arguments via their initialize methods that are populated by the config.
|
|
# This lets them gather data resources, build label sets etc.
|
|
[initialize]
|
|
vectors = ${paths.vectors}
|
|
# Extra resources for transfer-learning or pseudo-rehearsal
|
|
init_tok2vec = ${paths.init_tok2vec}
|
|
# Data and lookups for vocabulary
|
|
vocab_data = null
|
|
lookups = null
|
|
# Arguments passed to the tokenizer's initialize method
|
|
tokenizer = {}
|
|
# Arguments for initialize methods of the components (keyed by component)
|
|
components = {}
|
|
before_init = null
|
|
after_init = null
|