diff --git a/04_training_linear_models.ipynb b/04_training_linear_models.ipynb
index f91c9cc..fbf0062 100644
--- a/04_training_linear_models.ipynb
+++ b/04_training_linear_models.ipynb
@@ -1521,10 +1521,10 @@
     "for iteration in range(n_iterations):\n",
     "    logits = X_train.dot(Theta)\n",
     "    Y_proba = softmax(logits)\n",
-    "    loss = -np.mean(np.sum(Y_train_one_hot * np.log(Y_proba + epsilon), axis=1))\n",
-    "    error = Y_proba - Y_train_one_hot\n",
     "    if iteration % 500 == 0:\n",
+    "        loss = -np.mean(np.sum(Y_train_one_hot * np.log(Y_proba + epsilon), axis=1))\n",
     "        print(iteration, loss)\n",
+    "    error = Y_proba - Y_train_one_hot\n",
     "    gradients = 1/m * X_train.T.dot(error)\n",
     "    Theta = Theta - eta * gradients"
    ]
@@ -1590,12 +1590,12 @@
     "for iteration in range(n_iterations):\n",
     "    logits = X_train.dot(Theta)\n",
     "    Y_proba = softmax(logits)\n",
-    "    xentropy_loss = -np.mean(np.sum(Y_train_one_hot * np.log(Y_proba + epsilon), axis=1))\n",
-    "    l2_loss = 1/2 * np.sum(np.square(Theta[1:]))\n",
-    "    loss = xentropy_loss + alpha * l2_loss\n",
-    "    error = Y_proba - Y_train_one_hot\n",
     "    if iteration % 500 == 0:\n",
+    "        xentropy_loss = -np.mean(np.sum(Y_train_one_hot * np.log(Y_proba + epsilon), axis=1))\n",
+    "        l2_loss = 1/2 * np.sum(np.square(Theta[1:]))\n",
+    "        loss = xentropy_loss + alpha * l2_loss\n",
     "        print(iteration, loss)\n",
+    "    error = Y_proba - Y_train_one_hot\n",
     "    gradients = 1/m * X_train.T.dot(error) + np.r_[np.zeros([1, n_outputs]), alpha * Theta[1:]]\n",
     "    Theta = Theta - eta * gradients"
    ]
@@ -1793,7 +1793,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.8"
+   "version": "3.7.9"
   },
   "nav_menu": {},
   "toc": {