PyTorch预训练Bert模型的示例

pip install datasets
pip install transformers

from datasets import load_dataset

imdb = load_dataset('imdb')
print(imdb['train'][:3]) # 打印前3条训练数据

from transformers import AutoModelForSequenceClassification, AutoTokenizer

model_checkpoint = "bert-base-uncased"

tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
model = AutoModelForSequenceClassification.from_pretrained(model_checkpoint, num_labels=2)

def preprocessing_func(examples):
  return tokenizer(examples['text'], 
           padding=True,
           truncation=True, max_length=300)

batch_size = 16

encoded_data = imdb.map(preprocessing_func, batched=True, batch_size=batch_size)

from transformers import Trainer, TrainingArguments

args = TrainingArguments(
  'out',
  per_device_train_batch_size=batch_size,
  per_device_eval_batch_size=batch_size,
  learning_rate=5e-5,
  evaluation_strategy='epoch',
  num_train_epochs=10,
  load_best_model_at_end=True,
)

trainer = Trainer(
  model,
  args=args,
  train_dataset=encoded_data['train'],
  eval_dataset=encoded_data['test'],
  tokenizer=tokenizer
)

trainer.train()

trainer.evaluate()