def train_model_process(model, train_dataloader, val_dataloader, num_epochs):
    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    # Adam 优化器，learning rate = 0.001
    optimizer = torch.optim.**Adam**(model.parameters(), lr=0.001)
    # 损失函数为交叉熵函数
    criterion = nn.**CrossEntropyLoss**()

该函数写了模型如何训练，图上代码为设置optimizer 和 Loss function

1. Adam optimizer

CrossEntropyLoss