gradients didn't backward to the end about gpytorch HOT 4 CLOSED

import gpytorch
import torch
from gpytorch.kernels import RBFKernel, AdditiveGridInterpolationKernel
from gpytorch.likelihoods import GaussianLikelihood
from gpytorch.means import ConstantMean
from gpytorch.random_variables import GaussianRandomVariable
from torch import nn
from torch.autograd import Variable


class GP(gpytorch.models.ExactGP):
    def __init__(self, train_x, train_y, likelihood):
        super(GP, self).__init__(train_x, train_y, likelihood)
        self.embedding = nn.Embedding(10, 2)
        self.mean_module = ConstantMean(constant_bounds=[-1e-5, 1e-5])
        self.base_covar_module = RBFKernel(log_lengthscale_bounds=(-5, 6))
        self.covar_module = AdditiveGridInterpolationKernel(self.base_covar_module,
                                                            grid_size=100, grid_bounds=[(-10, 10)], n_components=2)
        self.register_parameter('log_outputscale', nn.Parameter(torch.Tensor([0])), bounds=(-5, 6))

    def forward(self, x):
        embs = self.embedding(x)
        mean_embs = self.mean_module(embs)
        covar_embs = self.covar_module(embs)
        covar_embs = covar_embs.mul(self.log_outputscale.exp())
        latent_pred = GaussianRandomVariable(mean_embs, covar_embs)
        return latent_pred


class GPRegressionModel(gpytorch.Module):
    def __init__(self, train_x, train_y):
        super(GPRegressionModel, self).__init__()
        self.likelihood = GaussianLikelihood()
        self.gp = GP(train_x, train_y, self.likelihood)

    def forward(self, x):
        return self.likelihood(self.gp(x))


if __name__ == '__main__':
    n = 10
    train_x = (torch.rand(n) * 10).type(torch.LongTensor)
    train_x = Variable(train_x)
    train_y = torch.randn(n)
    train_y = Variable(train_y)

    model = GPRegressionModel(train_x.data, train_y.data)
    output = model(train_x)
    loss = -model.gp.marginal_log_likelihood(model.likelihood, output, train_y)
    loss.backward()
    print('Embedding has gradients!', model.gp.embedding.weight.grad)

"""
Output:
('Embedding has gradients!', Variable containing:
 0.0000  0.0000
 0.0000  0.0000
 0.0000  0.0000
 0.0175 -0.0341
 0.0000  0.0000
-0.0136  0.0151
-0.0094  0.0722
 0.0290 -0.0124
 0.0907  0.0171
-0.0657 -0.1519
[torch.FloatTensor of size 10x2]
)
"""