Machine learning PyTorch，简单字符级RNN，can'；一个例子不过分

我是PyTorch框架的新手（主要来自Theano和Tensorflow）： 我已经按照介绍教程阅读了使用字符级别RNN的名称分类。 现在，我尝试将其应用于char级别的LSTM模型，以便获得使用该框架的一些实际经验。 基本上，我输入了char索引的模型序列，并将相同的序列作为模型的目标，但将来会移动一个。 然而，我不能过分适合一个简单的训练例子，我不知道我做错了什么。 如果有人能发现我的错误，那将非常有帮助。 这是我的密码：

class LSTMTxtGen(nn.Module):
def __init__(self, hidden_dim, n_layer, vocab_size):
    super(LSTMTxtGen, self).__init__()
    self.n_layer = n_layer
    self.hidden_dim = hidden_dim
    self.vocab_size = vocab_size

    self.lstm = nn.LSTM(vocab_size, hidden_dim, n_layer, batch_first=True)

    # The linear layer that maps from hidden state space to tag space
    #self.hidden = self.init_hidden()

def init_hidden(self, batch_size):
    # Before we've done anything, we dont have any hidden state.
    # Refer to the Pytorch documentation to see exactly
    # why they have this dimensionality.
    # The axes semantics are (num_layers, minibatch_size, hidden_dim)
    return (autograd.Variable(torch.zeros(self.n_layer, batch_size, 
                                          self.hidden_dim)),
            autograd.Variable(torch.zeros(self.n_layer, batch_size, 
                                          self.hidden_dim)))

def forward(self, seqs):
    self.hidden = self.init_hidden(seqs.size()[0])
    lstm_out, self.hidden = self.lstm(seqs, self.hidden)
    lstm_out = lstm_out.contiguous().view(-1, self.hidden_dim)
    lstm_out = nn.Linear(lstm_out.size(1), self.vocab_size)(lstm_out)
    return lstm_out

model = LSTMTxtGen (
hidden_dim = 50,
n_layer = 3,
vocab_size = 44,
)

print(Model)

criterion = nn.CrossEntropyLoss()
optimizer = optim.Adamax(model.parameters())

G = Data.batch_generator(5,100)
batch_per_epoch, to_idx, to_char = next(G)
X, Y = next(G)
for epoch in range(10):
    losses = []
    for batch_count in range(batch_per_epoch):
        model.zero_grad()

        #mode.hidden = model.init_hidden()

        #X, Y = next(G)
        X = autograd.Variable(torch.from_numpy(X))
        Y = autograd.Variable(torch.from_numpy(Y))

       preds = model(X)

       loss = criterion(preds.view(-1, model.vocab_size), Y.view(-1))
       loss.backward()
       optimizer.step()
       losses.append(loss)

       if (batch_count % 20 == 0):
           print('Loss: ', losses[-1])