关于多分类任务的一个报错

您好，我在完成一个多分类任务时遇到了一些困难。我运行指令python run.py --model TextCNN --word True --embedding random后报错Traceback (most recent call last):  

File "run.py", line 54, in <module>    train(config, model, train_iter, dev_iter, test_iter)  File "C:\Users\Administrator\Desktop\project\System\TextCNN\train_eval.py", line 47, in train   

 loss = F.cross_entropy(outputs, labels)  

File "C:\Users\Administrator\Desktop\project\System\venv\lib\site-packages\torch\nn\functional.py", line 2996, in cross_entropy    

return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing) 

IndexError: Target 48 is out of bounds。

我在网上看到的解释是输出层数跟我的标签数不匹配，我想问一下我应该改动哪里的代码呢？