I want to use the pretrained spacy en_core_web_trf model with the "ner" component, add "spancat" component and train it with the labelled data using prodigy. However, after running the train command I get the following error:
KeyError: "[E001] No component 'tok2vec' found in pipeline. Available names: ['transformer', 'tagger', 'parser', 'attribute_ruler', 'lemmatizer', 'ner']"
Similar question was already raised in the prodigy forum here and here
Some users have overcome this problem by changing the config file. However, in my case, I still continue receiving the same error.
My code in the command line:
python -m prodigy train ./model --spancat trans_span_labeled_dataset --config filled_config_changed.cfg --base-model en_core_web_trf
My config file:
[paths]
train = null
dev = null
vectors = null
[system]
gpu_allocator = "pytorch"
seed = 0
[nlp]
lang = "en"
pipeline = ["transformer","spancat"]
batch_size = 128
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
[components]
[components.spancat]
factory = "spancat"
max_positive = null
scorer = {"@scorers":"spacy.spancat_scorer.v1"}
spans_key = "sc"
threshold = 0.5
[components.spancat.model]
@architectures = "spacy.SpanCategorizer.v1"
[components.spancat.model.reducer]
@layers = "spacy.mean_max_reducer.v1"
hidden_size = 128
[components.spancat.model.scorer]
@layers = "spacy.LinearLogistic.v1"
nO = null
nI = null
[components.spancat.suggester]
@misc = "spacy.ngram_suggester.v1"
sizes = [1,2,3]
[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
before_update = 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]
spans_sc_f = 1.0
spans_sc_p = 0.0
spans_sc_r = 0.0
[pretraining]
[initialize]
vectors = ${paths.vectors}
vocab_data = null
lookups = null
before_init = null
after_init = null
[initialize.components]
[initialize.tokenizer]
My another config file that I tried to use:
[paths]
train = "./dvcstore/data/train.spacy"
dev = "./dvcstore/data/dev.spacy"
vectors = null
init_tok2vec = null
[system]
gpu_allocator = "pytorch"
seed = 0
[nlp]
lang = "en"
pipeline = ["ner"]
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
batch_size = 64
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
[components]
[components.ner]
factory = "ner"
incorrect_spans_key = "incorrect_spans"
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 = true
nO = null
[components.ner.model.tok2vec]
@architectures = "spacy-transformers.Tok2VecTransformer.v3"
name = "camembert-base"
grad_factor = 1.0
mixed_precision = false
pooling = {"@layers":"reduce_mean.v1"}
[components.ner.model.tok2vec.get_spans]
@span_getters = "spacy-transformers.strided_spans.v1"
window = 128
stride = 96
[components.ner.model.tok2vec.grad_scaler_config]
[components.ner.model.tok2vec.tokenizer_config]
use_fast = false
[components.ner.model.tok2vec.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]
train_corpus = "corpora.train"
dev_corpus = "corpora.dev"
seed = ${system:seed}
gpu_allocator = ${system:gpu_allocator}
dropout = 0.1
accumulate_gradient = 3
patience = 2000
max_epochs = 0
max_steps = 20000
eval_frequency = 500
frozen_components = []
before_to_disk = null
annotating_components = []
before_update = null
[training.batcher]
@batchers = "spacy.batch_by_padded.v1"
discard_oversize = false
get_length = null
size = 2000
buffer = 256
[training.logger]
@loggers = "spacy.ConsoleLogger.v1"
progress_bar = false
[training.optimizer]
@optimizers = "Adam.v1"
beta1 = 0.9
beta2 = 0.9992
L2_is_weight_decay = true
L2 = 0.001
grad_clip = 1.0
use_averages = true
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
pos_acc = null
morph_acc = null
morph_per_feat = null
dep_uas = null
dep_las = null
dep_las_per_type = null
sents_p = null
sents_r = null
sents_f = null
lemma_acc = null
speed = 0.0
[pretraining]
[initialize]
vectors = ${paths.vectors}
vocab_data = null
lookups = null
before_init = null
after_init = null
init_tok2vec = ${paths.init_tok2vec}
[initialize.components]
[initialize.components.ner]
[initialize.components.ner.labels]
@readers = "spacy.read_labels.v1"
path = "spacy_training/labels/ner.json"
require = false
[initialize.tokenizer]
Maybe a better solution would be to change the train recipe rather than config file?
I will appreciate any help.