Unable to train Spancat model, accuracy stuck at 0.0 #11412
Description
Losses decrease to 0 within 2000-3000 epochs, f, p, r scores do not go higher than 0 (image 1).
Then I tried a different datasets and got a result like this in image2. But when I tried the old dataset again with the same config, I stayed at 0 again, then I tried a different dataset and I was left at 0 again. I tried different different sizes for ngram_range_suggester but I couldn't find what is wrong!
image 1
image2
How to reproduce the behaviour
Here is the preprocess and config files that I used for training.
preprocess.py for creating .spacy files.
def main(
input_path: Path = typer.Argument(..., exists=True, dir_okay=False),
output_path: Path = typer.Argument(..., dir_okay=False),
):
nlp = spacy.blank("en")
doc_bin = DocBin()
for eg in srsly.read_jsonl(input_path):
doc = nlp.make_doc(eg["text"])
doc.spans['sc'] = []
for s in eg.get("spans", []):
span = doc.char_span(s["start"], s["end"], label=s["label"])
if span:
doc.spans["sc"].append(span)
if doc.spans:
doc_bin.add(doc)
doc_bin.to_disk(output_path)
print(f"Processed {len(doc_bin)} documents: {output_path.name}")
Here is my config.cfg
[paths]
train = null
dev = null
vectors = null
init_tok2vec = null
[system]
gpu_allocator = null
seed = 0
[nlp]
lang = "en"
pipeline = ["tok2vec","spancat"]
batch_size = 100
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.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = ${components.tok2vec.model.encode.width}
upstream = "*"
[components.spancat.suggester]
@misc = "spacy.ngram_range_suggester.v1"
min_size = 1
max_size = 30
[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 = true
[components.tok2vec.model.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 128
depth = 8
window_size = 1
maxout_pieces = 3
[corpora]
[corpora.dev]
@readers = "spacy.Corpus.v1"
path = ${paths.dev}
gold_preproc = false
limit = 0
augmenter = null
max_length = 0
[corpora.train]
@readers = "spacy.Corpus.v1"
path = ${paths.train}
gold_preproc = false
limit = 0
augmenter = null
max_length = 0
[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 = []
before_to_disk = null
annotating_components = []
[training.batcher]
@batchers = "spacy.batch_by_words.v1"
discard_oversize = true
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 = 0.0
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}
init_tok2vec = ${paths.init_tok2vec}
vocab_data = null
lookups = null
before_init = null
after_init = null
[initialize.components]
[initialize.tokenizer]
Info about spaCy
- spaCy version: 3.4.1
- Platform: macOS-12.3.1-x86_64-i386-64bit
- Python version: 3.9.13