remove snapshot logic

Author: soyr-redhat

mnist_sequential.ipynb

@@ -183,23 +183,12 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "epochs = 10\n",
-    "history = {\"loss\": [], \"accuracy\": [], \"val_loss\": [], \"val_accuracy\": []}\n",
-    "\n",
-    "# Epochs at which to capture prediction snapshots for visualization\n",
-    "snapshot_epochs = {1, 3, 5, 10}\n",
-    "epoch_snapshots = []"
-   ]
+   "source": "epochs = 10\nhistory = {\"loss\": [], \"accuracy\": [], \"val_loss\": [], \"val_accuracy\": []}"
   },
   {
    "cell_type": "markdown",
    "metadata": {},
-   "source": [
-    "## Training Phase: Forward and Backward Pass\n",
-    "\n",
-    "For each epoch, we iterate through batches of training data. The forward pass computes predictions, the loss measures error, and backpropagation (loss.backward()) calculates gradients. The optimizer then updates weights to reduce the error. We capture predictions at certain epochs to visualize learning progress."
-   ]
+   "source": "## Training Phase: Forward and Backward Pass\n\nFor each epoch, we iterate through batches of training data. The forward pass computes predictions, the loss measures error, and backpropagation (loss.backward()) calculates gradients. The optimizer then updates weights to reduce the error."
   },
   {
    "cell_type": "code",