def train(self, X_train, y_train, X_val=None, y_val=None, epochs=10, batch_size=1, clip_value=1.0):
        for epoch in range(epochs):
            epoch_losses = []
            for i in range(0, len(X_train), batch_size):
                batch_X = X_train[i:i + batch_size]
                batch_y = y_train[i:i + batch_size]
                losses = []

                for x, y_true in zip(batch_X, batch_y):
                    y_pred, caches = self.model.forward(x)
                    loss = self.compute_loss(y_pred, y_true.reshape(-1, 1))
                    losses.append(loss)

                    dy = y_pred - y_true.reshape(-1, 1)
                    grads = self.model.backward(dy, caches, clip_value=clip_value)
                    self.model.update_params(grads, self.learning_rate)

                batch_loss = np.mean(losses)
                epoch_losses.append(batch_loss)

            avg_epoch_loss = np.mean(epoch_losses)
            self.train_losses.append(avg_epoch_loss)

            if X_val is not None and y_val is not None:
                val_loss = self.validate(X_val, y_val)
                self.val_losses.append(val_loss)

                if epoch % 10 == 0:
                    print(f'Epoch {epoch + 1}/{epochs} - Loss: {avg_epoch_loss:.5f}, Val Loss: {val_loss:.5f}')

                self.early_stopping(val_loss)
                if self.early_stopping.early_stop:
                    print("Early stopping")
                    break
            else:
                print(f'Epoch {epoch + 1}/{epochs} - Loss: {avg_epoch_loss:.5f}')