如何恢复 NER 的 spacy transformer 训练
How to resume training in spacy transformers for NER
我已经创建了一个用于命名实体识别的 spacy 转换器模型。上次我训练直到它达到 90% 的准确率,我还有一个 model-best
目录,我可以从中加载我的训练模型进行预测。但是现在我有更多的数据样本,我想继续训练这个 spacy transformer。我看到我们可以通过更改 config.cfg
来做到这一点,但对 'what to change?'
毫无头绪
这是我的 config.cfg
之后 运行 python -m spacy init fill-config ./base_config.cfg ./config.cfg
:
[paths]
train = null
dev = null
vectors = null
init_tok2vec = null
[system]
gpu_allocator = "pytorch"
seed = 0
[nlp]
lang = "en"
pipeline = ["transformer","ner"]
batch_size = 128
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
[components]
[components.ner]
factory = "ner"
incorrect_spans_key = null
moves = null
scorer = {"@scorers":"spacy.ner_scorer.v1"}
update_with_oracle_cut_size = 100
[components.ner.model]
@architectures = "spacy.TransitionBasedParser.v2"
state_type = "ner"
extra_state_tokens = false
hidden_width = 64
maxout_pieces = 2
use_upper = false
nO = null
[components.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 = 4096
set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}
[components.transformer.model]
@architectures = "spacy-transformers.TransformerModel.v3"
name = "roberta-base"
mixed_precision = false
[components.transformer.model.get_spans]
@span_getters = "spacy-transformers.strided_spans.v1"
window = 128
stride = 96
[components.transformer.model.grad_scaler_config]
[components.transformer.model.tokenizer_config]
use_fast = true
[components.transformer.model.transformer_config]
[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 = 0
gold_preproc = false
limit = 0
augmenter = null
[training]
accumulate_gradient = 3
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
seed = ${system.seed}
gpu_allocator = ${system.gpu_allocator}
dropout = 0.1
patience = 1600
max_epochs = 0
max_steps = 20000
eval_frequency = 200
frozen_components = []
annotating_components = []
before_to_disk = null
[training.batcher]
@batchers = "spacy.batch_by_padded.v1"
discard_oversize = true
size = 2000
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]
如您所见,[initialize]
下有一个 'vectors' 参数,所以我尝试从 'model-best' 中给出向量,如下所示:
但它给了我这个错误
OSError: [E884] The pipeline could not be initialized because the vectors could not be found at './model-best/ner'. If your pipeline was already initialized/trained before, call 'resume_training' instead of 'initialize', or initialize only the components that are new.
对于那些想知道我走错了路的人。不,该目录存在。可以看到目录结构,
所以,请指导我如何成功地恢复以前的权重训练。
谢谢!
矢量设置与 transformer
或您要执行的操作无关。
在新配置中,您想使用 source
选项从现有管道加载组件。您可以将 [component]
块修改为仅包含 source
设置而不包含其他设置:
[components.ner]
source = "/path/to/model-best"
[components.transformer]
source = "/path/to/model-best"
我已经创建了一个用于命名实体识别的 spacy 转换器模型。上次我训练直到它达到 90% 的准确率,我还有一个 model-best
目录,我可以从中加载我的训练模型进行预测。但是现在我有更多的数据样本,我想继续训练这个 spacy transformer。我看到我们可以通过更改 config.cfg
来做到这一点,但对 'what to change?'
这是我的 config.cfg
之后 运行 python -m spacy init fill-config ./base_config.cfg ./config.cfg
:
[paths]
train = null
dev = null
vectors = null
init_tok2vec = null
[system]
gpu_allocator = "pytorch"
seed = 0
[nlp]
lang = "en"
pipeline = ["transformer","ner"]
batch_size = 128
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
[components]
[components.ner]
factory = "ner"
incorrect_spans_key = null
moves = null
scorer = {"@scorers":"spacy.ner_scorer.v1"}
update_with_oracle_cut_size = 100
[components.ner.model]
@architectures = "spacy.TransitionBasedParser.v2"
state_type = "ner"
extra_state_tokens = false
hidden_width = 64
maxout_pieces = 2
use_upper = false
nO = null
[components.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 = 4096
set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}
[components.transformer.model]
@architectures = "spacy-transformers.TransformerModel.v3"
name = "roberta-base"
mixed_precision = false
[components.transformer.model.get_spans]
@span_getters = "spacy-transformers.strided_spans.v1"
window = 128
stride = 96
[components.transformer.model.grad_scaler_config]
[components.transformer.model.tokenizer_config]
use_fast = true
[components.transformer.model.transformer_config]
[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 = 0
gold_preproc = false
limit = 0
augmenter = null
[training]
accumulate_gradient = 3
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
seed = ${system.seed}
gpu_allocator = ${system.gpu_allocator}
dropout = 0.1
patience = 1600
max_epochs = 0
max_steps = 20000
eval_frequency = 200
frozen_components = []
annotating_components = []
before_to_disk = null
[training.batcher]
@batchers = "spacy.batch_by_padded.v1"
discard_oversize = true
size = 2000
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]
如您所见,[initialize]
下有一个 'vectors' 参数,所以我尝试从 'model-best' 中给出向量,如下所示:
但它给了我这个错误
OSError: [E884] The pipeline could not be initialized because the vectors could not be found at './model-best/ner'. If your pipeline was already initialized/trained before, call 'resume_training' instead of 'initialize', or initialize only the components that are new.
对于那些想知道我走错了路的人。不,该目录存在。可以看到目录结构,
所以,请指导我如何成功地恢复以前的权重训练。
谢谢!
矢量设置与 transformer
或您要执行的操作无关。
在新配置中,您想使用 source
选项从现有管道加载组件。您可以将 [component]
块修改为仅包含 source
设置而不包含其他设置:
[components.ner]
source = "/path/to/model-best"
[components.transformer]
source = "/path/to/model-best"