根据文档训练huggingface transformers
NER模型,评估损失在几个时期后增加,但其他分数(准确性,准确性,召回率,f1)却不断提高。该行为似乎是意外的,对此效果是否有简单的解释?这可以取决于给定的数据吗?
model = TokenClassificationModel.from_pretrained('roberta-base', num_labels=len(tag_values))
model.train()
model.zero_grad()
for epoch in range(epochs):
for batch in range(batches):
-- train --
...
train_loss = model.evaluate(train_data)
validation_loss = model.evaluate(validation_data)