Hi,
In the spacy configuration in this page it is said that the default model for Textcat is TextCatEnsemble. However when I run prodigy without specifying my model the configuration file resulting says I'm using spacy.TextCatBOW.v2.
When I make my own configuration file adding the TextCatEnsemble.v2 as explained in the spacy website I get the following /opt/homebrew/lib/python3.9/site-packages/thinc/layers/layernorm.py:32: RuntimeWarning: divide by zero encountered in reciprocal d_xhat = N * dY - sum_dy - dist * var ** (-1.0) * sum_dy_dist
This is what I'm using for my configuration file: is the same as the one that prodigy created when I used the default I just changed the model for textcat_multilabel
[paths]
train = null
dev = null
vectors = null
init_tok2vec = null
[system]
gpu_allocator = null
seed = 0
[nlp]
lang = "en"
pipeline = ["tok2vec","tagger","parser","attribute_ruler","lemmatizer","ner","textcat_multilabel"]
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
batch_size = 256
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
[components]
[components.attribute_ruler]
factory = "attribute_ruler"
validate = false
[components.lemmatizer]
factory = "lemmatizer"
mode = "rule"
model = null
overwrite = false
[components.ner]
factory = "ner"
incorrect_spans_key = null
moves = null
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.Tok2Vec.v2"
[components.ner.model.tok2vec.embed]
@architectures = "spacy.MultiHashEmbed.v2"
width = 96
attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
rows = [5000,2500,2500,2500]
include_static_vectors = true
[components.ner.model.tok2vec.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 96
depth = 4
window_size = 1
maxout_pieces = 3
[components.parser]
factory = "parser"
learn_tokens = false
min_action_freq = 30
moves = null
update_with_oracle_cut_size = 100
[components.parser.model]
@architectures = "spacy.TransitionBasedParser.v2"
state_type = "parser"
extra_state_tokens = false
hidden_width = 64
maxout_pieces = 2
use_upper = true
nO = null
[components.parser.model.tok2vec]
@architectures = "spacy.Tok2Vec.v2"
[components.parser.model.tok2vec.embed]
@architectures = "spacy.MultiHashEmbed.v2"
width = 96
attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
rows = [5000,2500,2500,2500]
include_static_vectors = true
[components.parser.model.tok2vec.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 96
depth = 4
window_size = 1
maxout_pieces = 3
[components.tagger]
factory = "tagger"
[components.tagger.model]
@architectures = "spacy.Tagger.v1"
nO = null
[components.tagger.model.tok2vec]
@architectures = "spacy.Tok2Vec.v2"
[components.tagger.model.tok2vec.embed]
@architectures = "spacy.MultiHashEmbed.v2"
width = 96
attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
rows = [5000,2500,2500,2500]
include_static_vectors = true
[components.tagger.model.tok2vec.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 96
depth = 4
window_size = 1
maxout_pieces = 3
[components.textcat_multilabel]
factory = "textcat_multilabel"
threshold = 0.5
[components.textcat_multilabel.model]
@architectures = "spacy.TextCatEnsemble.v2"
nO = null
[components.textcat_multilabel.model.linear_model]
@architectures = "spacy.TextCatBOW.v2"
exclusive_classes = true
ngram_size = 1
no_output_layer = false
[components.tok2vec]
factory = "tok2vec"
[components.tok2vec.model]
@architectures = "spacy.Tok2Vec.v2"
[components.tok2vec.model.embed]
@architectures = "spacy.MultiHashEmbed.v2"
width = 64
rows = [2000, 2000, 1000, 1000, 1000, 1000]
attrs = ["ORTH", "LOWER", "PREFIX", "SUFFIX", "SHAPE", "ID"]
include_static_vectors = false
[components.tok2vec.model.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = ${model.tok2vec.embed.width}
window_size = 1
maxout_pieces = 3
depth = 2
[corpora]
@readers = "prodigy.MergedCorpus.v1"
eval_split = 0.5
sample_size = 1.0
ner = null
textcat = null
parser = null
tagger = null
senter = null
spancat = null
[corpora.textcat_multilabel]
@readers = "prodigy.TextCatCorpus.v1"
datasets = ["sectoral_annotations"]
eval_datasets = []
exclusive = false
[training]
train_corpus = "corpora.train"
dev_corpus = "corpora.dev"
seed = ${system:seed}
gpu_allocator = ${system:gpu_allocator}
dropout = 0.15
accumulate_gradient = 1
patience = 5000
max_epochs = 0
max_steps = 0
eval_frequency = 1000
frozen_components = ["tagger","parser","attribute_ruler","lemmatizer","ner"]
before_to_disk = null
annotating_components = []
[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 = "prodigy.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 = true
eps = 0.00000001
learn_rate = 0.001
[training.score_weights]
tag_acc = null
dep_uas = null
dep_las = null
dep_las_per_type = null
sents_p = null
sents_r = null
sents_f = null
lemma_acc = null
ents_f = null
ents_p = null
ents_r = null
ents_per_type = null
cats_score = 1.0
cats_score_desc = null
cats_micro_p = null
cats_micro_r = null
cats_micro_f = null
cats_macro_p = null
cats_macro_r = null
cats_macro_f = null
cats_macro_auc = null
cats_f_per_type = null
cats_macro_auc_per_type = null
[pretraining]
[initialize]
vectors = "en_core_web_lg"
init_tok2vec = ${paths.init_tok2vec}
vocab_data = null
lookups = null
before_init = null
after_init = null
[initialize.components]
[initialize.tokenizer]
