1--Trainer的使用
利用 Trainer 可以快速进行模型训练的配置,一般需要设置训练的模型以及训练相关参数等;
1-1--简单Demo代码
import evaluate
from datasets import load_dataset
from transformers import AutoTokenizer, AutoModelForSequenceClassification, Trainer, TrainingArguments, DataCollatorWithPadding
tokenizer = AutoTokenizer.from_pretrained("hfl/rbt3") # 分词
def process_function(examples):
tokenized_examples = tokenizer(examples["review"], max_length=128, truncation=True)
tokenized_examples["labels"] = examples["label"]
return tokenized_examples
# 创建评估函数
acc_metric = evaluate.load("accuracy")
f1_metirc = evaluate.load("f1")
def eval_metric(eval_predict):
predictions, labels = eval_predict
predictions = predictions.argmax(axis=-1)
acc = acc_metric.compute(predictions=predictions, references=labels)
f1 = f1_metirc.compute(predictions=predictions, references=labels)
acc.update(f1)
return acc
if __name__ == "__main__":
# 处理数据集
dataset = load_dataset("csv", data_files="./ChnSentiCorp_htl_all.csv", split="train")
dataset = dataset.filter(lambda x: x["review"] is not None) # 过滤字段 review 为 None 的数据
datasets = dataset.train_test_split(test_size = 0.1) # 划分训练和测试集
tokenized_datasets = datasets.map(process_function, batched = True, remove_columns = datasets["train"].column_names)
# 初始化模型
model = AutoModelForSequenceClassification.from_pretrained("hfl/rbt3")
# print(model.config)
# 训练参数
train_args = TrainingArguments(output_dir="./checkpoints", # 输出文件夹
per_device_train_batch_size=64, # 训练时的batch_size
per_device_eval_batch_size=128, # 验证时的batch_size
logging_steps=10, # log 打印的频率
evaluation_strategy="epoch", # 评估策略
num_train_epochs = 5, # 训练epoch数
save_strategy="epoch", # 保存策略
save_total_limit=3, # 最大保存数
learning_rate=2e-5, # 学习率
weight_decay=0.01, # weight_decay
metric_for_best_model="f1", # 设定评估指标
load_best_model_at_end=True) # 训练完成后加载最优模型
# 创建trainer
trainer = Trainer(model = model, # 训练模型
args = train_args, # 训练参数
train_dataset = tokenized_datasets["train"], # 训练集
eval_dataset = tokenized_datasets["test"], # 测试集
data_collator = DataCollatorWithPadding(tokenizer=tokenizer),
compute_metrics = eval_metric) # 评估函数
# 模型训练
trainer.train()
# 模型评估
trainer.evaluate(tokenized_datasets["test"])
# 模型测试
trainer.predict(tokenized_datasets["test"])
print("All done!")