如何使用pytorch动态图属性来并行训练具有不同超参数的模型？

import torch
import torch.nn as nn
import torch.optim as optim
import torch.multiprocessing as mp

class Model(nn.Module):
    def __init__(self, hyperparam):
        super(Model, self).__init__()
        self.hyperparam = hyperparam
        self.fc = nn.Linear(10, 1)

    def forward(self, x):
        x = self.fc(x)
        return x

def train(hyperparam):
    model = Model(hyperparam)
    criterion = nn.MSELoss()
    optimizer = optim.SGD(model.parameters(), lr=hyperparam)

    # 在这里执行训练过程，例如循环迭代等

def main():
    hyperparams = [0.1, 0.01, 0.001]  # 不同的超参数值

    processes = []
    for hyperparam in hyperparams:
        p = mp.Process(target=train, args=(hyperparam,))
        p.start()
        processes.append(p)

    for p in processes:
        p.join()

if __name__ == '__main__':
    main()