Hi Ines,
I am trying to train a model for spans (I have a single label), however when I train the model all the performance scores are zero, in other words the model learned nothing. I also tried your en_core_web_sm solution and it did not work.
Here is my config file:
[paths]
train = null
dev = null
vectors = null
init_tok2vec = null
[system]
gpu_allocator = null
seed = 0
[nlp]
lang = "en"
pipeline = ["tok2vec","spancat"]
batch_size = 1000
disabled =
before_creation = null
after_creation = null
after_pipeline_creation = null
tokenizer = {"at 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.model.tok2vec]
architectures = "spacy.Tok2VecListener.v1"
width = ${components.tok2vec.model.encode.width}
upstream = "*"
[components.spancat.suggester]
misc = "spacy.ngram_suggester.v1"
sizes = [1,2,3]
[components.tok2vec]
factory = "tok2vec"
[components.tok2vec.model]
architectures = "spacy.Tok2Vec.v2"
[components.tok2vec.model.embed]
architectures = "spacy.MultiHashEmbed.v2"
width = ${components.tok2vec.model.encode.width}
attrs = ["ORTH","SHAPE"]
rows = [5000,2500]
include_static_vectors = false
[components.tok2vec.model.encode]
architectures = "spacy.MaxoutWindowEncoder.v2"
width = 96
depth = 4
window_size = 1
maxout_pieces = 3
[corpora]
readers = "prodigy.MergedCorpus.v1"
eval_split = 0.2
sample_size = 1.0
ner = null
textcat = null
textcat_multilabel = null
parser = null
tagger = null
senter = null
[corpora.spancat]
readers = "prodigy.SpanCatCorpus.v1"
datasets = ["ops_spans_not_custom"]
eval_datasets =
spans_key = "sc"
[training]
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
seed = ${system.seed}
gpu_allocator = ${system.gpu_allocator}
dropout = 0.1
accumulate_gradient = 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_words.v1"
discard_oversize = false
tolerance = 0.2
get_length = null
[training.batcher.size]
schedules = "compounding.v1"
start = 100
stop = 1000
compound = 1.001
t = 0.0
[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
learn_rate = 0.001
[training.score_weights]
spans_sc_f = 1.0
spans_sc_p = 0.0
spans_sc_r = 0.0
[pretraining]
[initialize]
vectors = ${paths.vectors}
before_init = {"callbacks":"customize_tokenizer"}
init_tok2vec = ${paths.init_tok2vec}
vocab_data = null
lookups = null
after_init = null
[initialize.components]
[initialize.tokenizer]
here is how my spans look like (they all have underlines):
car_number_123_irf
and here is my training recipe:
!prodigy train ./model3 --spancat dataset_manual -c config.cfg -F functions.py --verbose
I am using a custom tokenizer, and this is my functions.py:
def make_customize_tokenizer():
def customize_tokenizer(nlp):
special_cases = {"A.M.": [{"ORTH": "A.M."}],
"P.M.": [{"ORTH": "P.M."}],
"U.S.": [{"ORTH": "U.S."}]}
prefix_re = re.compile(r'''''')
suffix_re = re.compile(r'''()."']|('s))$''')
infix_re = re.compile(r'''[-~:_/\.,]''')
# remove a suffix
nlp.tokenizer = Tokenizer(nlp.vocab, rules=special_cases,
prefix_search=prefix_re.search,
suffix_search=suffix_re.search,
infix_finditer=infix_re.finditer,
token_match=nlp.tokenizer.token_match,
url_match=nlp.Defaults.url_match)
return customize_tokenizer
I have also tried the standard tokenizers but the training step skips all tagged spans and the training performance is zero.
