No GPU Usage apparent in Google Cloud Vm with pytorch already installed and Cuda10

I have been using in my machine a network, that is nothing really special. I wanted to do it faster so I started using google cloud. But I notice something weird that my machine with a GTX 1050 ti was faster than a V100 GPU. This didn’t add up so I checked the usage and it seems that even though I put some stress by creating a big network and passing a lot of data to it the gpu by using a simple .cuda() in both the model and the data: there wasn’t ussage shown in nvidia-smi command as shown in the image

you can check my code here:

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    print("The device is:",device,torch.cuda.get_device_name(0),"and how many are they",torch.cuda.device_count())
    # # We load the training data 
    Samples , Ocupancy, num_samples, Samples_per_slice = common.load_samples(args.samples_filename)
    Samples = Samples * args.scaling_todo
    # Divide into Slices
    Organize_Positions,Orginezed_Ocupancy, batch_size = common.organize_sample_data(Samples,Ocupancy,num_samples,Samples_per_slice,args.num_batches)
    phi = common.MLP(3, 1).cuda()
    x_test = torch.from_numpy(Organize_Positions.astype(np.float32)).cuda()
    y_test = torch.from_numpy(Orginezed_Ocupancy.astype(np.float32)).cuda()
    all_data = common.CustomDataset(x_test, y_test)

    #Dive into Slices the data
    Slice_data = DataLoader(dataset=all_data, batch_size = batch_size, shuffle=False) # only take batch_size = n/b TODO Don't shuffle
    #Chunky_data = DataLoader(dataset=Slice_data, batch_size =  chunch_size, shuffle=False)

    criterion = torch.nn.BCEWithLogitsLoss()
    optimizer = torch.optim.Adam(phi.parameters(), lr = 0.0001)
    epoch = args.num_epochs

    fit_start_time = time.time()
    for epoch in range(epoch):
        curr_epoch_loss = 0
        batch = 0
        for x_batch, y_batch in Slice_data:
            x_train = x_batch
            y_train = y_batch

            y_pred = phi(x_train)
            loss = criterion(y_pred.squeeze(), y_train.squeeze())
            curr_epoch_loss += loss
            print('Batch {}: train loss: {}'.format(batch, loss.item()))    # Backward pass

            optimizer.step() # Optimizes only phi parameters
        print('Epoch {}: train loss: {}'.format(epoch, loss.item()))

    fit_end_time = time.time()
    print("Total time = %f" % (fit_end_time - fit_start_time))
    # Save Model{'state_dict': phi.state_dict()}, args.model_filename)

and the model here:

class MLP(nn.Module):
    def __init__(self, in_dim: int, out_dim: int):
        self.in_dim = in_dim
        self.out_dim = out_dim
        self.fc1 = nn.Linear(in_dim, 128)
        self.fc1_bn = nn.BatchNorm1d(128)
        self.fc2 = nn.Linear(128, 256)
        self.fc2_bn = nn.BatchNorm1d(256)
        self.fc3 = nn.Linear(256, 512)
        self.fc3_bn = nn.BatchNorm1d(512)
        self.fc4 = nn.Linear(512, 512)
        self.fc4_bn = nn.BatchNorm1d(512)
        self.fc5 = nn.Linear(512, out_dim,bias=False)
        self.relu = nn.LeakyReLU()

    def forward(self, x):
        x = self.relu(self.fc1_bn(self.fc1(x)))
        x = self.relu(self.fc2_bn(self.fc2(x)))# leaky
        x = self.relu(self.fc3_bn(self.fc3(x)))
        x = self.relu(self.fc4_bn(self.fc4(x)))
        x = self.fc5(x)
        return x

class CustomDataset(Dataset):
    def __init__(self, x_tensor, y_tensor):
        self.x = x_tensor
        self.y = y_tensor
    def __getitem__(self, index):
        return (self.x[index], self.y[index])

    def __len__(self):
        return len(self.x)