Add validation dataset to hyperparameter scan

Code/python/notebooks/hyperparameter_scan.py

@@ -26,7 +26,13 @@ if not pathlib.Path("dataset.pt").exists():
 results = []
 for step in [1, 5, 10, 30]:
     dataset = dataloader.SaveDataset(torch.load("dataset.pt"), device="cuda", step=step)
-
+    dataset_length = len(dataset)
+    dataset, val_dataset = torch.utils.data.random_split(
+        dataset,
+        [int(0.8 * dataset_length), dataset_length - int(0.8 * dataset_length)],
+        generator=torch.Generator().manual_seed(42)
+    )
+    print(f"Starting hyperparameter scan for step={step}")
     for base_name, base_model in [
         ("RNN", models.ThreeInputRNN),
         ("LSTM", models.ThreeInputLSTM),
@@ -63,6 +69,16 @@ for step in [1, 5, 10, 30]:
                     loss = sum(loss_history) / len(loss_history)
                     scheduler.step(loss)
                     print(f"Epoch {epoch}: loss={loss}, lr={optimizer.param_groups[0]['lr']}")
+                with torch.no_grad():
+                    val_loss_history = []
+                    for X_f, X_t, y, X_c in torch.utils.data.DataLoader(val_dataset, batch_size=256):
+                        warm_up_steps = 450 // step
+                        pred_steps = 150 // step
+                        y_pred, _ = model(X_t, X_f, X_c, warm_up_steps, pred_steps)
+                        v_loss = criterion(y_pred, y)
+                        val_loss_history.append(v_loss.item())
+                    loss = sum(val_loss_history) / len(val_loss_history)
+                    print(f"Validation loss: {loss}")
                 torch.save(model.state_dict(), f"{base_name}_hs{hidden_size}_rs{rnn_size}_step{step}.pt")
                 results.append((base_name, hidden_size, rnn_size, step, loss))