100x -> 50x

Author: rasbt

appendix-E/01_main-chapter-code/appendix-E.ipynb

@@ -776,7 +776,7 @@
     "id": "b8b6819e-ef7a-4f0d-841a-1b467496bef9"
    },
    "source": [
-    "- As we can see, we reduced the number of trainable parameters by almost 100x when using LoRA\n",
+    "- As we can see, we reduced the number of trainable parameters by almost 50x when using LoRA\n",
     "- Let's now double-check whether the layers have been modified as intended by printing the model architecture"
    ]
   },
@@ -1474,14 +1474,6 @@
    "source": [
     "- As we can see based on the relatively high accuracy values above, the LoRA finetuning was successful"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "baa472da-44cf-42a9-8e59-6ddf7979bcd5",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {