Performance measures of PyTorch / Skorch NN are all zero

Question

I am trying the predict prices and I used PyTorch and Skorch to build a neural network for the predictions. I found this helpful article that shows how to do it for classification: https://towardsdatascience.com/pycaret-skorch-build-pytorch-neural-networks-using-minimal-code-57079e197f33#:~:text=Yes%2C%20you%20heard%20it%20right,which%20is%20what%20PyCaret%20expects!. I changed the code such that it now runs for regression. However, the performance measures all output zero. Can someone help me out?

This is the code I currently have:

`from skorch import NeuralNetRegressor
from skorch.helper import DataFrameTransformer
from skorch.callbacks import EarlyStopping

target = "Price"

exp = setup(data = train, 
             test_data = test,
             target = target)

class RegressorModule(nn.Module):
    def __init__(
            self,
            input_size= 13,
            num_units=150,
            num_units_d1=100,
            num_units_d2=50,
            nonlin=F.relu,
    ):
        super(RegressorModule, self).__init__()
        self.num_units = num_units
        self.nonlin = nonlin

        self.dense0 = nn.LazyLinear(input_size, num_units)
        self.dense1 = nn.LazyLinear(num_units, num_units_d1)
        self.dense2 = nn.LazyLinear(num_units_d1, num_units_d2)
        self.output = nn.LazyLinear(num_units_d2, 1)

    def forward(self, X, **kwargs):
        X = self.nonlin(self.dense0(X))
        X = self.nonlin(self.dense1(X))
        X = self.nonlin(self.dense2(X))
        X = self.output(X)
        return X
    
    def training_step(self, batch, **kwargs):
        data, target = batch
        predictions = self.forward(data)
        loss = F.mse_loss(predictions, target)
        rmse = torch.sqrt(loss)
        self.log('train_rmse', rmse, on_step=True, on_epoch=True, prog_bar=True)
        return loss

class MyNet(NeuralNetRegressor):
    def fit(self, X, y):
        if y.ndim == 1:
            y = y.values.reshape(-1, 1)
        return super().fit(X, y)

net_regr = MyNet(
    module=RegressorModule(input_size=13),
    max_epochs=20,
    lr=0.1,
    train_split=None,
)

nn_pipe = Pipeline(
    [
        ("transform", DataFrameTransformer()),
        ("net", net_regr),
    ]
)
skorch_model = exp.create_model(nn_pipe)`

enter image description here

and this image shows the output.