我正在使用spacy 2.1.8
并spacy-pytorch-transformers 0.4.0
训练一个文本分类器。我的代码受到他们示例的强烈启发,但模型没有学习任何东西,这似乎是由于损失一直为 0 造成的。我的代码的最小(非)工作示例如下:
nlp = spacy.load("en_pytt_xlnetbasecased_lg")
textcategorizer = nlp.create_pipe("pytt_textcat", config={"exclusive_classes": True, "architecture": "softmax_last_hidden"})
for label in labels:
textcategorizer.add_label(label)
nlp.add_pipe(textcategorizer, last=True)
optimizer = nlp.resume_training()
for epoch in range(num_of_epochs):
np.random.shuffle(train)
losses = Counter()
for step, batch in enumerate(minibatch(train, size=batch_size)):
optimizer.pytt_lr = 0.005
texts, cats = zip(*batch)
_, cats = preprocessed_labels_to_categories_for_training_and_eval(cats)
nlp.update(texts, cats, sgd=optimizer, losses=losses, drop=0.1)
我已经两次和三次检查了相关变量,例如cats
and texts
,是否包含有效和正确的值。
有什么我想念的吗?