I have built a lstm model that takes input data with 3 features and the rolling window size is 18. While training the model in jupyter notebook, it shows the training process is going on but does not show any accuracy parameters. It seems like the training process is stuck somewhere. I had implemented the same model with the same data in Keras, it gave those training errors quite quickly.

Here is the model that I built.

```
class LSTMnetwork(nn.Module):
def __init__(self,input_size=3,hidden_size1=24, hidden_size2=50, hidden_size3=20,output_size=1):
super().__init__()
self.hidden_size1 = hidden_size1
self.hidden_size2 = hidden_size2
self.hidden_size3 = hidden_size3
# Add an LSTM and dropout layer:
self.lstm1 = nn.LSTM(input_size,hidden_size1)
self.dropout1 = nn.Dropout(p=0.2)
# Add second LSTM and dropout layer:
self.lstm2 = nn.LSTM(hidden_size1,hidden_size2)
self.dropout2 = nn.Dropout(p=0.2)
# Add a fully-connected layer:
self.fc1 = nn.Linear(hidden_size2,hidden_size3)
# Add another fully-connected layer:
self.fc2 = nn.Linear(hidden_size3,output_size)
# Initialize h0 and c0:
self.hidden1 = (torch.zeros(1,1,self.hidden_size1),
torch.zeros(1,1,self.hidden_size1))
# Initialize h1 and c1:
self.hidden2 = (torch.zeros(1,1,self.hidden_size2),
torch.zeros(1,1,self.hidden_size2))
def forward(self,seq):
lstm1_out, self.hidden1 = self.lstm1(seq.view(len(seq),1,-1), self.hidden1)
dropout1 = self.dropout1(lstm1_out)
lstm2_out, self.hidden2 = self.lstm2(dropout1.view(len(dropout1),1,-1), self.hidden2)
dropout2 = self.dropout2(lstm2_out)
fc1_out = F.relu(self.fc1(dropout2))
fc2_out = self.fc2(fc1_out)
return fc2_out[-1]
model = LSTMnetwork()
criterion = nn.MSELoss()
optimizer = torch.optim.Adam(model.parameters(), lr = 0.001)
#training the model
epochs = 10
#to monitor training time
start_time = time.time()
for epoch in range(epochs):
for seq, label in train_data:
#reset the parameters and hidden states
optimizer.zero_grad()
model.hidden1 = (torch.zeros(1,1,model.hidden_size1),
torch.zeros(1,1,model.hidden_size1))
model.hidden2 = (torch.zeros(1,1,model.hidden_size2),
torch.zeros(1,1,model.hidden_size2))
y_pred_train = model(seq)
loss = criterion(y_pred_train, label.reshape(1,1))
loss.backward()
optimizer.step()
# print training result
print(f'Epoch: {epoch+1:2} Loss: {loss.item():10.8f}')
print(f'\nDuration: {time.time() - start_time:.0f} seconds')
```