diff --git a/appendix-A/01_main-chapter-code/code-part1.ipynb b/appendix-A/01_main-chapter-code/code-part1.ipynb
index 8520a2e..a9413b5 100644
--- a/appendix-A/01_main-chapter-code/code-part1.ipynb
+++ b/appendix-A/01_main-chapter-code/code-part1.ipynb
@@ -46,7 +46,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "2.2.1\n"
+      "2.4.0\n"
      ]
     }
    ],
@@ -658,13 +658,13 @@
      "output_type": "stream",
      "text": [
       "Parameter containing:\n",
-      "tensor([[ 0.0956,  0.1280, -0.0696,  ...,  0.0961,  0.0631,  0.1349],\n",
-      "        [ 0.0983,  0.0580, -0.0574,  ...,  0.0981,  0.0370,  0.0516],\n",
-      "        [-0.0429, -0.1411, -0.1399,  ...,  0.0767,  0.0019,  0.1400],\n",
+      "tensor([[ 0.1182,  0.0606, -0.1292,  ..., -0.1126,  0.0735, -0.0597],\n",
+      "        [-0.0249,  0.0154, -0.0476,  ..., -0.1001, -0.1288,  0.1295],\n",
+      "        [ 0.0641,  0.0018, -0.0367,  ..., -0.0990, -0.0424, -0.0043],\n",
       "        ...,\n",
-      "        [-0.0777, -0.0726,  0.1273,  ..., -0.0613,  0.0491, -0.1381],\n",
-      "        [-0.0830, -0.0969, -0.0473,  ...,  0.0762,  0.1318, -0.1174],\n",
-      "        [ 0.0468, -0.0213,  0.0387,  ...,  0.0639,  0.0927, -0.0668]],\n",
+      "        [ 0.0618,  0.0867,  0.1361,  ..., -0.0254,  0.0399,  0.1006],\n",
+      "        [ 0.0842, -0.0512, -0.0960,  ..., -0.1091,  0.1242, -0.0428],\n",
+      "        [ 0.0518, -0.1390, -0.0923,  ..., -0.0954, -0.0668, -0.0037]],\n",
       "       requires_grad=True)\n"
      ]
     }
@@ -1264,7 +1264,7 @@
    ],
    "source": [
     "model = NeuralNetwork(2, 2) # needs to match the original model exactly\n",
-    "model.load_state_dict(torch.load(\"model.pth\"))"
+    "model.load_state_dict(torch.load(\"model.pth\", weights_only=True))"
    ]
   },
   {
@@ -1340,7 +1340,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.11"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,
diff --git a/appendix-A/01_main-chapter-code/code-part2.ipynb b/appendix-A/01_main-chapter-code/code-part2.ipynb
index ce32269..b02cdaf 100644
--- a/appendix-A/01_main-chapter-code/code-part2.ipynb
+++ b/appendix-A/01_main-chapter-code/code-part2.ipynb
@@ -2,7 +2,9 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "metadata": {},
+   "metadata": {
+    "id": "AAAnDw04iAm4"
+   },
    "source": [
     "<table style=\"width:100%\">\n",
     "<tr>\n",
@@ -54,14 +56,14 @@
      "base_uri": "https://localhost:8080/"
     },
     "id": "RM7kGhwMF_nO",
-    "outputId": "ac60b048-b81f-4bb0-90fa-1ca474f04e9a"
+    "outputId": "b1872617-aacd-46fa-e5f3-f130fd81b246"
    },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "2.0.1+cu118\n"
+      "2.4.0+cu121\n"
      ]
     }
    ],
@@ -79,7 +81,7 @@
      "base_uri": "https://localhost:8080/"
     },
     "id": "OXLCKXhiUkZt",
-    "outputId": "39fe5366-287e-47eb-cc34-3508d616c4f9"
+    "outputId": "e9ca3c58-d92c-4c8b-a9c9-cd7fcc1fedb4"
    },
    "outputs": [
     {
@@ -102,18 +104,15 @@
      "base_uri": "https://localhost:8080/"
     },
     "id": "MTTlfh53Va-T",
-    "outputId": "f31d8bbe-577f-4db4-9939-02e66b9f96d1"
+    "outputId": "bae76cb5-d1d3-441f-a7c5-93a161e2e86a"
    },
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "tensor([5., 7., 9.])"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "tensor([5., 7., 9.])\n"
+     ]
     }
    ],
    "source": [
@@ -125,13 +124,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "Z4LwTNw7Vmmb",
-    "outputId": "1c025c6a-e3ed-4c7c-f5fd-86c14607036e"
+    "outputId": "9ad97923-bc8e-4c49-88bf-48dc1de56804"
    },
    "outputs": [
     {
@@ -151,24 +150,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 5,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/",
-     "height": 184
+     "height": 158
     },
     "id": "tKT6URN1Vuft",
-    "outputId": "e6f01e7f-d9cf-44cb-cc6d-46fc7907d5c0"
+    "outputId": "8396eb18-47c8-47a1-c1b6-8bcb9480fb52"
    },
    "outputs": [
     {
      "ename": "RuntimeError",
-     "evalue": "ignored",
+     "evalue": "Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!",
      "output_type": "error",
      "traceback": [
       "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
       "\u001b[0;31mRuntimeError\u001b[0m                              Traceback (most recent call last)",
-      "\u001b[0;32m<ipython-input-7-4ff3c4d20fc3>\u001b[0m in \u001b[0;36m<cell line: 2>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0mtensor_1\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtensor_1\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"cpu\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtensor_1\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mtensor_2\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
+      "\u001b[0;32m/tmp/ipykernel_2321/2079609735.py\u001b[0m in \u001b[0;36m<cell line: 2>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0mtensor_1\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtensor_1\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"cpu\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtensor_1\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mtensor_2\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
       "\u001b[0;31mRuntimeError\u001b[0m: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!"
      ]
     }
@@ -189,7 +188,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 6,
    "metadata": {
     "id": "GyY59cjieitv"
    },
@@ -215,7 +214,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 7,
    "metadata": {
     "id": "v41gKqEJempa"
    },
@@ -243,7 +242,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 8,
    "metadata": {
     "id": "UPGVRuylep8Y"
    },
@@ -271,7 +270,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 9,
    "metadata": {
     "id": "drhg6IXofAXh"
    },
@@ -302,13 +301,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 10,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "7jaS5sqPWCY0",
-    "outputId": "84c74615-38f2-48b8-eeda-b5912fed1d3a"
+    "outputId": "8a5cd93d-671c-4abf-d5cd-97845f300ffd"
    },
    "outputs": [
     {
@@ -362,7 +361,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 11,
    "metadata": {
     "id": "4qrlmnPPe7FO"
    },
@@ -391,13 +390,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 12,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "1_-BfkfEf4HX",
-    "outputId": "473bf21d-5880-4de3-fc8a-051d75315b94"
+    "outputId": "9453154f-0a5b-4a44-a3c9-f010e08d5a2c"
    },
    "outputs": [
     {
@@ -406,7 +405,7 @@
        "1.0"
       ]
      },
-     "execution_count": 27,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -417,13 +416,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 13,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "iYtXKBGEgKss",
-    "outputId": "508edd84-3fb7-4d04-cb23-9df0c3d24170"
+    "outputId": "d6cc870a-34de-490e-e5d3-23e6956744bd"
    },
    "outputs": [
     {
@@ -432,7 +431,7 @@
        "1.0"
       ]
      },
-     "execution_count": 21,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -443,21 +442,27 @@
   },
   {
    "cell_type": "markdown",
-   "metadata": {},
+   "metadata": {
+    "id": "nc2LGFVbiAnB"
+   },
    "source": [
     "### A.9.3 Training with multiple GPUs"
    ]
   },
   {
    "cell_type": "markdown",
-   "metadata": {},
+   "metadata": {
+    "id": "cOUza9iQiAnC"
+   },
    "source": [
     "See [DDP-script.py](DDP-script.py)"
    ]
   },
   {
    "cell_type": "markdown",
-   "metadata": {},
+   "metadata": {
+    "id": "YOYk5Fh7iAnC"
+   },
    "source": [
     "<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/appendix-a_compressed/12.webp\" width=\"600px\">\n",
     "<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/appendix-a_compressed/13.webp\" width=\"600px\">"
@@ -485,7 +490,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.10.14"
   }
  },
  "nbformat": 4,
diff --git a/ch02/01_main-chapter-code/ch02.ipynb b/ch02/01_main-chapter-code/ch02.ipynb
index 0dfdf3b..24f15c5 100644
--- a/ch02/01_main-chapter-code/ch02.ipynb
+++ b/ch02/01_main-chapter-code/ch02.ipynb
@@ -46,7 +46,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "torch version: 2.3.1\n",
+      "torch version: 2.4.0\n",
       "tiktoken version: 0.7.0\n"
      ]
     }
@@ -1244,7 +1244,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "PyTorch version: 2.3.1\n"
+      "PyTorch version: 2.4.0\n"
      ]
     }
    ],
diff --git a/ch02/01_main-chapter-code/dataloader.ipynb b/ch02/01_main-chapter-code/dataloader.ipynb
index 3a9ecaf..93c3811 100644
--- a/ch02/01_main-chapter-code/dataloader.ipynb
+++ b/ch02/01_main-chapter-code/dataloader.ipynb
@@ -38,9 +38,39 @@
     "This notebook contains the main takeaway, the data loading pipeline without the intermediate steps."
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "2b4e8f2d-cb81-41a3-8780-a70b382e18ae",
+   "metadata": {},
+   "source": [
+    "Packages that are being used in this notebook:"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 1,
+   "id": "c7ed6fbe-45ac-40ce-8ea5-4edb212565e1",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "torch version: 2.4.0\n",
+      "tiktoken version: 0.7.0\n"
+     ]
+    }
+   ],
+   "source": [
+    "from importlib.metadata import version\n",
+    "\n",
+    "print(\"torch version:\", version(\"torch\"))\n",
+    "print(\"tiktoken version:\", version(\"tiktoken\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
    "id": "0ed4b7db-3b47-4fd3-a4a6-5f4ed5dd166e",
    "metadata": {},
    "outputs": [],
@@ -107,7 +137,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "id": "664397bc-6daa-4b88-90aa-e8fc1fbd5846",
    "metadata": {},
    "outputs": [],
@@ -125,7 +155,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "id": "d3664332-e6bb-447e-8b96-203aafde8b24",
    "metadata": {},
    "outputs": [
diff --git a/ch02/01_main-chapter-code/exercise-solutions.ipynb b/ch02/01_main-chapter-code/exercise-solutions.ipynb
index d7dc38e..52d8f90 100644
--- a/ch02/01_main-chapter-code/exercise-solutions.ipynb
+++ b/ch02/01_main-chapter-code/exercise-solutions.ipynb
@@ -28,6 +28,36 @@
     "# Chapter 2 Exercise solutions"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "2ed9978c-6d8e-401b-9731-bec3802cbb96",
+   "metadata": {},
+   "source": [
+    "Packages that are being used in this notebook:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "78b55ed6-3312-4e30-89b8-51dc8a4a908f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "torch version: 2.4.0\n",
+      "tiktoken version: 0.7.0\n"
+     ]
+    }
+   ],
+   "source": [
+    "from importlib.metadata import version\n",
+    "\n",
+    "print(\"torch version:\", version(\"torch\"))\n",
+    "print(\"tiktoken version:\", version(\"tiktoken\"))"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "6f678e62-7bcb-4405-86ae-dce94f494303",
@@ -38,7 +68,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "id": "7614337f-f639-42c9-a99b-d33f74fa8a03",
    "metadata": {},
    "outputs": [],
@@ -50,7 +80,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "id": "4f235d87-be85-4ddf-95a6-af59fca13d82",
    "metadata": {},
    "outputs": [
@@ -69,7 +99,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "id": "45e4e8f0-3272-48bb-96f6-cced5584ceea",
    "metadata": {},
    "outputs": [
@@ -93,7 +123,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "id": "664397bc-6daa-4b88-90aa-e8fc1fbd5846",
    "metadata": {},
    "outputs": [
@@ -103,7 +133,7 @@
        "[33901]"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -114,7 +144,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "d3664332-e6bb-447e-8b96-203aafde8b24",
    "metadata": {},
    "outputs": [
@@ -124,7 +154,7 @@
        "[86]"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -135,7 +165,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "id": "2773c09d-c136-4372-a2be-04b58d292842",
    "metadata": {},
    "outputs": [
@@ -145,7 +175,7 @@
        "[343]"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -156,7 +186,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "id": "8a6abd32-1e0a-4038-9dd2-673f47bcdeb5",
    "metadata": {},
    "outputs": [
@@ -166,7 +196,7 @@
        "[86]"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -177,7 +207,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "id": "26ae940a-9841-4e27-a1df-b83fc8a488b3",
    "metadata": {},
    "outputs": [
@@ -187,7 +217,7 @@
        "[220]"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -198,7 +228,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 10,
    "id": "a606c39a-6747-4cd8-bb38-e3183f80908d",
    "metadata": {},
    "outputs": [
@@ -208,7 +238,7 @@
        "[959]"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -219,7 +249,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 11,
    "id": "47c7268d-8fdc-4957-bc68-5be6113f45a7",
    "metadata": {},
    "outputs": [
@@ -229,7 +259,7 @@
        "'Akwirw ier'"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -248,7 +278,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 12,
    "id": "4d50af16-937b-49e0-8ffd-42d30cbb41c9",
    "metadata": {},
    "outputs": [],
@@ -310,7 +340,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 13,
    "id": "0128eefa-d7c8-4f76-9851-566dfa7c3745",
    "metadata": {},
    "outputs": [
@@ -323,7 +353,7 @@
        "        [ 402,  271]])"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -340,7 +370,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 14,
    "id": "ff5c1e90-c6de-4a87-adf6-7e19f603291c",
    "metadata": {},
    "outputs": [
@@ -353,7 +383,7 @@
        "        [  402,   271, 10899,  2138,   257,  7026, 15632,   438]])"
       ]
      },
-     "execution_count": 13,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -385,7 +415,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.6"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,
diff --git a/ch03/01_main-chapter-code/ch03.ipynb b/ch03/01_main-chapter-code/ch03.ipynb
index 2c74134..7e0fb31 100644
--- a/ch03/01_main-chapter-code/ch03.ipynb
+++ b/ch03/01_main-chapter-code/ch03.ipynb
@@ -46,7 +46,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "torch version: 2.2.2\n"
+      "torch version: 2.4.0\n"
      ]
     }
    ],
diff --git a/ch03/01_main-chapter-code/exercise-solutions.ipynb b/ch03/01_main-chapter-code/exercise-solutions.ipynb
index 49ae7f2..d41aa5e 100644
--- a/ch03/01_main-chapter-code/exercise-solutions.ipynb
+++ b/ch03/01_main-chapter-code/exercise-solutions.ipynb
@@ -28,6 +28,27 @@
     "# Chapter 3 Exercise solutions"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "513b627b-c197-44bd-99a2-756391c8a1cd",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "torch version: 2.4.0\n"
+     ]
+    }
+   ],
+   "source": [
+    "from importlib.metadata import version\n",
+    "\n",
+    "import torch\n",
+    "print(\"torch version:\", version(\"torch\"))"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "33dfa199-9aee-41d4-a64b-7e3811b9a616",
@@ -38,7 +59,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 2,
    "id": "5fee2cf5-61c3-4167-81b5-44ea155bbaf2",
    "metadata": {},
    "outputs": [],
@@ -59,7 +80,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 58,
+   "execution_count": 3,
    "id": "62ea289c-41cd-4416-89dd-dde6383a6f70",
    "metadata": {},
    "outputs": [],
@@ -92,7 +113,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 59,
+   "execution_count": 4,
    "id": "7b035143-f4e8-45fb-b398-dec1bd5153d4",
    "metadata": {},
    "outputs": [],
@@ -123,7 +144,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 60,
+   "execution_count": 5,
    "id": "7591d79c-c30e-406d-adfd-20c12eb448f6",
    "metadata": {},
    "outputs": [],
@@ -135,7 +156,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 61,
+   "execution_count": 6,
    "id": "ddd0f54f-6bce-46cc-a428-17c2a56557d0",
    "metadata": {},
    "outputs": [
@@ -150,7 +171,7 @@
        "        [-0.5299, -0.1081]], grad_fn=<MmBackward0>)"
       ]
      },
-     "execution_count": 61,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -161,7 +182,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 62,
+   "execution_count": 7,
    "id": "340908f8-1144-4ddd-a9e1-a1c5c3d592f5",
    "metadata": {},
    "outputs": [
@@ -176,7 +197,7 @@
        "        [-0.5299, -0.1081]], grad_fn=<MmBackward0>)"
       ]
      },
-     "execution_count": 62,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -320,7 +341,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.6"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,
diff --git a/ch03/01_main-chapter-code/multihead-attention.ipynb b/ch03/01_main-chapter-code/multihead-attention.ipynb
index 10a5422..b58ee71 100644
--- a/ch03/01_main-chapter-code/multihead-attention.ipynb
+++ b/ch03/01_main-chapter-code/multihead-attention.ipynb
@@ -364,14 +364,6 @@
     "\n",
     "print(\"context_vecs.shape:\", context_vecs.shape)"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "f1d965a5-9b98-4554-8646-7ecd497874cb",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
diff --git a/ch04/01_main-chapter-code/ch04.ipynb b/ch04/01_main-chapter-code/ch04.ipynb
index b734330..e843959 100644
--- a/ch04/01_main-chapter-code/ch04.ipynb
+++ b/ch04/01_main-chapter-code/ch04.ipynb
@@ -38,9 +38,9 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "matplotlib version: 3.7.2\n",
-      "torch version: 2.2.1\n",
-      "tiktoken version: 0.5.1\n"
+      "matplotlib version: 3.9.0\n",
+      "torch version: 2.4.0\n",
+      "tiktoken version: 0.7.0\n"
      ]
     }
    ],
@@ -630,7 +630,7 @@
    "outputs": [
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 800x300 with 2 Axes>"
       ]
@@ -1107,7 +1107,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 24,
    "id": "ef94fd9c-4e9d-470d-8f8e-dd23d1bb1f64",
    "metadata": {},
    "outputs": [
@@ -1154,7 +1154,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 25,
    "id": "84fb8be4-9d3b-402b-b3da-86b663aac33a",
    "metadata": {},
    "outputs": [
@@ -1186,7 +1186,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 26,
    "id": "e3b43233-e9b8-4f5a-b72b-a263ec686982",
    "metadata": {},
    "outputs": [
@@ -1215,7 +1215,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 27,
    "id": "95a22e02-50d3-48b3-a4e0-d9863343c164",
    "metadata": {},
    "outputs": [
@@ -1244,7 +1244,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 28,
    "id": "5131a752-fab8-4d70-a600-e29870b33528",
    "metadata": {},
    "outputs": [
@@ -1339,7 +1339,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 29,
    "id": "c9b428a9-8764-4b36-80cd-7d4e00595ba6",
    "metadata": {},
    "outputs": [],
@@ -1393,7 +1393,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 30,
    "id": "3d7e3e94-df0f-4c0f-a6a1-423f500ac1d3",
    "metadata": {},
    "outputs": [
@@ -1418,7 +1418,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 31,
    "id": "a72a9b60-de66-44cf-b2f9-1e638934ada4",
    "metadata": {},
    "outputs": [
@@ -1455,7 +1455,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 32,
    "id": "053d99f6-5710-4446-8d52-117fb34ea9f6",
    "metadata": {},
    "outputs": [
diff --git a/ch04/01_main-chapter-code/exercise-solutions.ipynb b/ch04/01_main-chapter-code/exercise-solutions.ipynb
index 83683e8..9bc2e62 100644
--- a/ch04/01_main-chapter-code/exercise-solutions.ipynb
+++ b/ch04/01_main-chapter-code/exercise-solutions.ipynb
@@ -28,6 +28,27 @@
     "# Chapter 4 Exercise solutions"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "5b2fac7a-fdcd-437c-b1c4-0b35a31cd489",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "torch version: 2.4.0\n"
+     ]
+    }
+   ],
+   "source": [
+    "from importlib.metadata import version\n",
+    "\n",
+    "import torch\n",
+    "print(\"torch version:\", version(\"torch\"))"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "5fea8be3-30a1-4623-a6d7-b095c6c1092e",
@@ -38,7 +59,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "id": "2751b0e5-ffd3-4be2-8db3-e20dd4d61d69",
    "metadata": {},
    "outputs": [],
@@ -60,7 +81,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "id": "1bcaffd1-0cf6-4f8f-bd53-ab88a37f443e",
    "metadata": {},
    "outputs": [
@@ -79,7 +100,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "id": "c1dd06c1-ab6c-4df7-ba73-f9cd54b31138",
    "metadata": {},
    "outputs": [
@@ -141,7 +162,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "id": "90185dea-81ca-4cdc-aef7-4aaf95cba946",
    "metadata": {},
    "outputs": [],
@@ -205,7 +226,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "2587e011-78a4-479c-a8fd-961cc40a5fd4",
    "metadata": {},
    "outputs": [
@@ -262,7 +283,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "id": "5fee2cf5-61c3-4167-81b5-44ea155bbaf2",
    "metadata": {},
    "outputs": [],
@@ -282,7 +303,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "id": "5aa1b0c1-d78a-48fc-ad08-4802458b43f7",
    "metadata": {},
    "outputs": [],
@@ -351,7 +372,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "id": "1d013d32-c275-4f42-be21-9010f1537227",
    "metadata": {},
    "outputs": [],
diff --git a/ch05/01_main-chapter-code/ch05.ipynb b/ch05/01_main-chapter-code/ch05.ipynb
index 4b470f6..792bcc4 100644
--- a/ch05/01_main-chapter-code/ch05.ipynb
+++ b/ch05/01_main-chapter-code/ch05.ipynb
@@ -41,10 +41,10 @@
      "output_type": "stream",
      "text": [
       "matplotlib version: 3.9.0\n",
-      "numpy version: 1.25.2\n",
-      "tiktoken version: 0.5.1\n",
-      "torch version: 2.2.2\n",
-      "tensorflow version: 2.15.0\n"
+      "numpy version: 1.26.4\n",
+      "tiktoken version: 0.7.0\n",
+      "torch version: 2.4.0\n",
+      "tensorflow version: 2.16.1\n"
      ]
     }
    ],
@@ -400,7 +400,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "id": "c990ead6-53cd-49a7-a6d1-14d8c1518249",
    "metadata": {},
    "outputs": [
@@ -445,7 +445,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 8,
    "id": "54aef09c-d6e3-4238-8653-b3a1b0a1077a",
    "metadata": {
     "colab": {
@@ -485,7 +485,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 9,
    "id": "31402a67-a16e-4aeb-977e-70abb9c9949b",
    "metadata": {
     "colab": {
@@ -519,7 +519,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 10,
    "id": "9b003797-161b-4d98-81dc-e68320e09fec",
    "metadata": {
     "colab": {
@@ -563,7 +563,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 11,
    "id": "176ddf35-1c5f-4d7c-bf17-70f3e7069bd4",
    "metadata": {},
    "outputs": [
@@ -606,7 +606,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 12,
    "id": "695d6f64-5084-4c23-aea4-105c9e38cfe4",
    "metadata": {
     "colab": {
@@ -643,7 +643,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 13,
    "id": "0e17e027-ab9f-4fb5-ac9b-a009b831c122",
    "metadata": {
     "colab": {
@@ -681,7 +681,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 14,
    "id": "62d0816e-b29a-4c8f-a9a5-a167562de978",
    "metadata": {
     "colab": {
@@ -715,7 +715,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 15,
    "id": "168952a1-b964-4aa7-8e49-966fa26add54",
    "metadata": {
     "colab": {
@@ -779,7 +779,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 16,
    "id": "654fde37-b2a9-4a20-a8d3-0206c056e2ff",
    "metadata": {},
    "outputs": [],
@@ -810,7 +810,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 17,
    "id": "6kgJbe4ehI4q",
    "metadata": {
     "colab": {
@@ -836,7 +836,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 18,
    "id": "j2XPde_ThM_e",
    "metadata": {
     "colab": {
@@ -862,7 +862,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 19,
    "id": "6b46a952-d50a-4837-af09-4095698f7fd1",
    "metadata": {
     "colab": {
@@ -918,7 +918,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 20,
    "id": "0959c855-f860-4358-8b98-bc654f047578",
    "metadata": {},
    "outputs": [],
@@ -957,7 +957,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 21,
    "id": "f37b3eb0-854e-4895-9898-fa7d1e67566e",
    "metadata": {},
    "outputs": [],
@@ -994,7 +994,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 22,
    "id": "ca0116d0-d229-472c-9fbf-ebc229331c3e",
    "metadata": {},
    "outputs": [
@@ -1038,7 +1038,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 23,
    "id": "eb860488-5453-41d7-9870-23b723f742a0",
    "metadata": {
     "colab": {
@@ -1083,7 +1083,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 24,
    "id": "7b9de31e-4096-47b3-976d-b6d2fdce04bc",
    "metadata": {
     "id": "7b9de31e-4096-47b3-976d-b6d2fdce04bc"
@@ -1127,7 +1127,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 25,
    "id": "56f5b0c9-1065-4d67-98b9-010e42fc1e2a",
    "metadata": {},
    "outputs": [
@@ -1135,7 +1135,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Training loss: 10.98758347829183\n",
+      "Training loss: 10.987583584255642\n",
       "Validation loss: 10.98110580444336\n"
      ]
     }
@@ -1186,7 +1186,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 26,
    "id": "Mtp4gY0ZO-qq",
    "metadata": {
     "id": "Mtp4gY0ZO-qq"
@@ -1262,7 +1262,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 27,
    "id": "3422000b-7aa2-485b-92df-99372cd22311",
    "metadata": {
     "colab": {
@@ -1323,7 +1323,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 28,
    "id": "0WSRu2i0iHJE",
    "metadata": {
     "colab": {
@@ -1434,7 +1434,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 29,
    "id": "2734cee0-f6f9-42d5-b71c-fa7e0ef28b6d",
    "metadata": {},
    "outputs": [
@@ -1501,7 +1501,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 30,
    "id": "01a5ce39-3dc8-4c35-96bc-6410a1e42412",
    "metadata": {},
    "outputs": [
@@ -1543,7 +1543,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 31,
    "id": "6400572f-b3c8-49e2-95bc-433e55c5b3a1",
    "metadata": {},
    "outputs": [
@@ -1563,7 +1563,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 32,
    "id": "b23b863e-252a-403c-b5b1-62bc0a42319f",
    "metadata": {},
    "outputs": [
@@ -1615,7 +1615,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 33,
    "id": "0759e4c8-5362-467c-bec6-b0a19d1ba43d",
    "metadata": {},
    "outputs": [],
@@ -1633,7 +1633,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 34,
    "id": "2e66e613-4aca-4296-a984-ddd0d80c6578",
    "metadata": {},
    "outputs": [
@@ -1677,7 +1677,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 35,
    "id": "e4600713-c51e-4f53-bf58-040a6eb362b8",
    "metadata": {},
    "outputs": [
@@ -1710,7 +1710,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 36,
    "id": "9dfb48f0-bc3f-46a5-9844-33b6c9b0f4df",
    "metadata": {},
    "outputs": [
@@ -1779,7 +1779,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 37,
    "id": "2a7f908a-e9ec-446a-b407-fb6dbf05c806",
    "metadata": {},
    "outputs": [
@@ -1802,7 +1802,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 38,
    "id": "753865ed-79c5-48b1-b9f2-ccb132ff1d2f",
    "metadata": {},
    "outputs": [
@@ -1826,7 +1826,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": 39,
    "id": "4844f000-c329-4e7e-aa89-16a2c4ebee43",
    "metadata": {},
    "outputs": [
@@ -1862,7 +1862,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 41,
+   "execution_count": 40,
    "id": "8e318891-bcc0-4d71-b147-33ce55febfa3",
    "metadata": {},
    "outputs": [],
@@ -1908,7 +1908,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 41,
    "id": "aa2a0d7d-0457-42d1-ab9d-bd67683e7ed8",
    "metadata": {},
    "outputs": [
@@ -1964,7 +1964,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": 42,
    "id": "3d67d869-ac04-4382-bcfb-c96d1ca80d47",
    "metadata": {},
    "outputs": [],
@@ -1982,14 +1982,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 43,
    "id": "9d57d914-60a3-47f1-b499-5352f4c457cb",
    "metadata": {},
    "outputs": [],
    "source": [
     "model = GPTModel(GPT_CONFIG_124M)\n",
     "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
-    "model.load_state_dict(torch.load(\"model.pth\", map_location=device))\n",
+    "model.load_state_dict(torch.load(\"model.pth\", map_location=device, weights_only=True))\n",
     "model.eval();"
    ]
   },
@@ -2004,7 +2004,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
+   "execution_count": 44,
    "id": "bbd175bb-edf4-450e-a6de-d3e8913c6532",
    "metadata": {},
    "outputs": [],
@@ -2019,12 +2019,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": 45,
    "id": "8a0c7295-c822-43bf-9286-c45abc542868",
    "metadata": {},
    "outputs": [],
    "source": [
-    "checkpoint = torch.load(\"model_and_optimizer.pth\")\n",
+    "checkpoint = torch.load(\"model_and_optimizer.pth\", weights_only=True)\n",
     "\n",
     "model = GPTModel(GPT_CONFIG_124M)\n",
     "model.load_state_dict(checkpoint[\"model_state_dict\"])\n",
@@ -2072,7 +2072,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 47,
+   "execution_count": 46,
    "id": "fb9fdf02-972a-444e-bf65-8ffcaaf30ce8",
    "metadata": {},
    "outputs": [],
@@ -2082,7 +2082,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": 47,
    "id": "a0747edc-559c-44ef-a93f-079d60227e3f",
    "metadata": {},
    "outputs": [
@@ -2090,8 +2090,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "TensorFlow version: 2.15.0\n",
-      "tqdm version: 4.66.2\n"
+      "TensorFlow version: 2.16.1\n",
+      "tqdm version: 4.66.4\n"
      ]
     }
    ],
@@ -2102,7 +2102,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": 48,
    "id": "c5bc89eb-4d39-4287-9b0c-e459ebe7f5ed",
    "metadata": {},
    "outputs": [],
@@ -2121,21 +2121,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 50,
+   "execution_count": 49,
    "id": "76271dd7-108d-4f5b-9c01-6ae0aac4b395",
    "metadata": {},
    "outputs": [
     {
-     "name": "stderr",
+     "name": "stdout",
      "output_type": "stream",
      "text": [
-      "checkpoint: 100%|███████████████████████████| 77.0/77.0 [00:00<00:00, 58.8kiB/s]\n",
-      "encoder.json: 100%|███████████████████████| 1.04M/1.04M [00:00<00:00, 2.70MiB/s]\n",
-      "hparams.json: 100%|█████████████████████████| 90.0/90.0 [00:00<00:00, 27.8kiB/s]\n",
-      "model.ckpt.data-00000-of-00001: 100%|███████| 498M/498M [00:30<00:00, 16.1MiB/s]\n",
-      "model.ckpt.index: 100%|███████████████████| 5.21k/5.21k [00:00<00:00, 1.18MiB/s]\n",
-      "model.ckpt.meta: 100%|██████████████████████| 471k/471k [00:00<00:00, 2.22MiB/s]\n",
-      "vocab.bpe: 100%|████████████████████████████| 456k/456k [00:00<00:00, 2.04MiB/s]\n"
+      "File already exists and is up-to-date: gpt2/124M/checkpoint\n",
+      "File already exists and is up-to-date: gpt2/124M/encoder.json\n",
+      "File already exists and is up-to-date: gpt2/124M/hparams.json\n",
+      "File already exists and is up-to-date: gpt2/124M/model.ckpt.data-00000-of-00001\n",
+      "File already exists and is up-to-date: gpt2/124M/model.ckpt.index\n",
+      "File already exists and is up-to-date: gpt2/124M/model.ckpt.meta\n",
+      "File already exists and is up-to-date: gpt2/124M/vocab.bpe\n"
      ]
     }
    ],
@@ -2145,7 +2145,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 51,
+   "execution_count": 50,
    "id": "b1a31951-d971-4a6e-9c43-11ee1168ec6a",
    "metadata": {},
    "outputs": [
@@ -2163,7 +2163,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 52,
+   "execution_count": 51,
    "id": "857c8331-130e-46ba-921d-fa35d7a73cfe",
    "metadata": {},
    "outputs": [
@@ -2181,7 +2181,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 53,
+   "execution_count": 52,
    "id": "c48dac94-8562-4a66-84ef-46c613cdc4cd",
    "metadata": {},
    "outputs": [
@@ -2241,7 +2241,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 54,
+   "execution_count": 53,
    "id": "9fef90dd-0654-4667-844f-08e28339ef7d",
    "metadata": {},
    "outputs": [],
@@ -2274,7 +2274,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 55,
+   "execution_count": 54,
    "id": "f9a92229-c002-49a6-8cfb-248297ad8296",
    "metadata": {},
    "outputs": [],
@@ -2287,7 +2287,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 56,
+   "execution_count": 55,
    "id": "f22d5d95-ca5a-425c-a9ec-fc432a12d4e9",
    "metadata": {},
    "outputs": [],
@@ -2369,7 +2369,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 57,
+   "execution_count": 56,
    "id": "1f690253-f845-4347-b7b6-43fabbd2affa",
    "metadata": {},
    "outputs": [
diff --git a/ch05/01_main-chapter-code/exercise-solutions.ipynb b/ch05/01_main-chapter-code/exercise-solutions.ipynb
index 67cb3d4..e9501e3 100644
--- a/ch05/01_main-chapter-code/exercise-solutions.ipynb
+++ b/ch05/01_main-chapter-code/exercise-solutions.ipynb
@@ -28,6 +28,35 @@
     "# Chapter 5 Exercise solutions"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "37aa4692-2357-4d88-b072-6d2d988d7f4f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "numpy version: 1.26.4\n",
+      "tiktoken version: 0.7.0\n",
+      "torch version: 2.4.0\n",
+      "tensorflow version: 2.16.1\n"
+     ]
+    }
+   ],
+   "source": [
+    "from importlib.metadata import version\n",
+    "\n",
+    "pkgs = [\"numpy\", \n",
+    "        \"tiktoken\", \n",
+    "        \"torch\",\n",
+    "        \"tensorflow\" # For OpenAI's pretrained weights\n",
+    "       ]\n",
+    "for p in pkgs:\n",
+    "    print(f\"{p} version: {version(p)}\")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "5fea8be3-30a1-4623-a6d7-b095c6c1092e",
@@ -58,7 +87,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "id": "42dda298-3014-4c36-8d63-97c210bcf4e8",
    "metadata": {},
    "outputs": [],
@@ -109,7 +138,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "id": "b5605236-e300-4844-aea7-509d868efbdd",
    "metadata": {},
    "outputs": [
@@ -172,7 +201,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "id": "1d4163c0-22ad-4f5b-8e20-b7420e9dbfc6",
    "metadata": {},
    "outputs": [
@@ -182,7 +211,7 @@
        "tensor(0.0430)"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -250,7 +279,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "id": "a61a4034-797a-4635-bf42-ddfff1b07125",
    "metadata": {},
    "outputs": [],
@@ -275,13 +304,13 @@
     "\n",
     "tokenizer = tiktoken.get_encoding(\"gpt2\")\n",
     "model = GPTModel(GPT_CONFIG_124M)\n",
-    "model.load_state_dict(torch.load(\"model.pth\"))\n",
+    "model.load_state_dict(torch.load(\"model.pth\", weights_only=True))\n",
     "model.eval();"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "ee95a272-b852-43b4-9827-ea7e1dbd5724",
    "metadata": {},
    "outputs": [],
@@ -292,7 +321,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "id": "4ab43658-3240-484a-9072-a40a0ed85be6",
    "metadata": {},
    "outputs": [
@@ -322,7 +351,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "id": "ebb22d06-393a-42d3-ab64-66646d33b39b",
    "metadata": {},
    "outputs": [
@@ -352,7 +381,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "id": "75469f24-47cc-458d-a200-fe64c648131d",
    "metadata": {},
    "outputs": [
@@ -400,7 +429,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 10,
    "id": "94eae6ba-d9fd-417a-8e31-fc39e9299870",
    "metadata": {},
    "outputs": [],
@@ -424,7 +453,7 @@
     "\n",
     "tokenizer = tiktoken.get_encoding(\"gpt2\")\n",
     "\n",
-    "checkpoint = torch.load(\"model_and_optimizer.pth\")\n",
+    "checkpoint = torch.load(\"model_and_optimizer.pth\", weights_only=True)\n",
     "model = GPTModel(GPT_CONFIG_124M)\n",
     "model.load_state_dict(checkpoint[\"model_state_dict\"])\n",
     "model.to(device)\n",
@@ -444,7 +473,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 11,
    "id": "b5a78470-0652-4abd-875a-664e23c07c36",
    "metadata": {},
    "outputs": [],
@@ -507,7 +536,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 12,
    "id": "ab4693dc-1359-47a7-8110-1e90f514a49e",
    "metadata": {},
    "outputs": [
@@ -576,7 +605,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 13,
    "id": "68d162d6-bbb9-4d6d-82ee-1c410694f872",
    "metadata": {},
    "outputs": [],
@@ -604,7 +633,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 14,
    "id": "d8373461-7dad-47da-a489-3e23f0799b23",
    "metadata": {},
    "outputs": [
@@ -630,7 +659,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 15,
    "id": "cdd44873-d6c2-4471-a20f-f639b09fdcd3",
    "metadata": {},
    "outputs": [],
@@ -655,7 +684,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 16,
    "id": "c7d562e4-33f6-4611-9b75-6ad1cb441d3b",
    "metadata": {},
    "outputs": [],
@@ -670,7 +699,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 17,
    "id": "46eda9ea-ccb0-46ee-931b-3c07502b2544",
    "metadata": {},
    "outputs": [],
@@ -725,7 +754,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 18,
    "id": "4e3574a2-687d-47a2-a2f6-457fe9d595f1",
    "metadata": {},
    "outputs": [
@@ -733,8 +762,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Training loss: 3.7547483444213867\n",
-      "Validation loss: 3.5596189498901367\n"
+      "Training loss: 3.7547486888037787\n",
+      "Validation loss: 3.5596182346343994\n"
      ]
     }
    ],
@@ -759,23 +788,29 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 19,
    "id": "1a79a4b6-fe8f-40c2-a018-e731dcf391b3",
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "checkpoint: 100%|███████████████████████████| 77.0/77.0 [00:00<00:00, 43.5kiB/s]\n",
+      "encoder.json: 100%|███████████████████████| 1.04M/1.04M [00:00<00:00, 2.75MiB/s]\n",
+      "hparams.json: 100%|█████████████████████████| 91.0/91.0 [00:00<00:00, 60.2kiB/s]\n",
+      "model.ckpt.data-00000-of-00001: 100%|█████| 6.23G/6.23G [06:02<00:00, 17.2MiB/s]\n",
+      "model.ckpt.index: 100%|████████████████████| 20.7k/20.7k [00:00<00:00, 171kiB/s]\n",
+      "model.ckpt.meta: 100%|████████████████████| 1.84M/1.84M [00:00<00:00, 4.27MiB/s]\n",
+      "vocab.bpe: 100%|████████████████████████████| 456k/456k [00:00<00:00, 1.73MiB/s]\n"
+     ]
+    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "File already exists and is up-to-date: gpt2/1558M/checkpoint\n",
-      "File already exists and is up-to-date: gpt2/1558M/encoder.json\n",
-      "File already exists and is up-to-date: gpt2/1558M/hparams.json\n",
-      "File already exists and is up-to-date: gpt2/1558M/model.ckpt.data-00000-of-00001\n",
-      "File already exists and is up-to-date: gpt2/1558M/model.ckpt.index\n",
-      "File already exists and is up-to-date: gpt2/1558M/model.ckpt.meta\n",
-      "File already exists and is up-to-date: gpt2/1558M/vocab.bpe\n",
-      "Training loss: 3.3046313656700983\n",
-      "Validation loss: 3.1195149421691895\n"
+      "Training loss: 3.3046312861972384\n",
+      "Validation loss: 3.1195147037506104\n"
      ]
     }
    ],
@@ -832,7 +867,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 20,
    "id": "31e0972b-e85e-4904-a0f5-24c3eacd5fa2",
    "metadata": {},
    "outputs": [],
@@ -858,7 +893,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 21,
    "id": "b641ee88-f9d4-43ec-a787-e34199eed356",
    "metadata": {},
    "outputs": [
@@ -902,7 +937,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 22,
    "id": "c98f56f4-98fc-43b4-9ee5-726e9d17c73f",
    "metadata": {},
    "outputs": [],
@@ -912,7 +947,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 23,
    "id": "b1f7853c-6e81-4f1f-a1d0-61e2c7d33a20",
    "metadata": {},
    "outputs": [
@@ -957,7 +992,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.11"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,
diff --git a/ch05/01_main-chapter-code/gpt_train.py b/ch05/01_main-chapter-code/gpt_train.py
index 0061e5e..cb1facf 100644
--- a/ch05/01_main-chapter-code/gpt_train.py
+++ b/ch05/01_main-chapter-code/gpt_train.py
@@ -239,4 +239,4 @@ if __name__ == "__main__":
     # Save and load model
     torch.save(model.state_dict(), "model.pth")
     model = GPTModel(GPT_CONFIG_124M)
-    model.load_state_dict(torch.load("model.pth"))
+    model.load_state_dict(torch.load("model.pth"), weights_only=True)
diff --git a/ch06/01_main-chapter-code/ch06.ipynb b/ch06/01_main-chapter-code/ch06.ipynb
index f4ffc34..71952a4 100644
--- a/ch06/01_main-chapter-code/ch06.ipynb
+++ b/ch06/01_main-chapter-code/ch06.ipynb
@@ -48,12 +48,12 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "matplotlib version: 3.7.2\n",
-      "numpy version: 1.25.2\n",
-      "tiktoken version: 0.5.1\n",
-      "torch version: 2.2.2\n",
-      "tensorflow version: 2.15.0\n",
-      "pandas version: 2.0.3\n"
+      "matplotlib version: 3.9.0\n",
+      "numpy version: 1.26.4\n",
+      "tiktoken version: 0.7.0\n",
+      "torch version: 2.4.0\n",
+      "tensorflow version: 2.16.1\n",
+      "pandas version: 2.2.2\n"
      ]
     }
    ],
@@ -181,7 +181,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "sms_spam_collection/SMSSpamCollection.tsv already exists. Skipping download and extraction.\n"
+      "File downloaded and saved as sms_spam_collection/SMSSpamCollection.tsv\n"
      ]
     }
    ],
@@ -846,7 +846,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 15,
    "id": "2992d779-f9fb-4812-a117-553eb790a5a9",
    "metadata": {
     "id": "2992d779-f9fb-4812-a117-553eb790a5a9"
@@ -892,16 +892,16 @@
    },
    "outputs": [
     {
-     "name": "stdout",
+     "name": "stderr",
      "output_type": "stream",
      "text": [
-      "File already exists and is up-to-date: gpt2/124M/checkpoint\n",
-      "File already exists and is up-to-date: gpt2/124M/encoder.json\n",
-      "File already exists and is up-to-date: gpt2/124M/hparams.json\n",
-      "File already exists and is up-to-date: gpt2/124M/model.ckpt.data-00000-of-00001\n",
-      "File already exists and is up-to-date: gpt2/124M/model.ckpt.index\n",
-      "File already exists and is up-to-date: gpt2/124M/model.ckpt.meta\n",
-      "File already exists and is up-to-date: gpt2/124M/vocab.bpe\n"
+      "checkpoint: 100%|███████████████████████████| 77.0/77.0 [00:00<00:00, 24.2kiB/s]\n",
+      "encoder.json: 100%|███████████████████████| 1.04M/1.04M [00:00<00:00, 2.53MiB/s]\n",
+      "hparams.json: 100%|█████████████████████████| 90.0/90.0 [00:00<00:00, 37.4kiB/s]\n",
+      "model.ckpt.data-00000-of-00001: 100%|███████| 498M/498M [00:24<00:00, 20.7MiB/s]\n",
+      "model.ckpt.index: 100%|████████████████████| 5.21k/5.21k [00:00<00:00, 924kiB/s]\n",
+      "model.ckpt.meta: 100%|██████████████████████| 471k/471k [00:00<00:00, 1.89MiB/s]\n",
+      "vocab.bpe: 100%|████████████████████████████| 456k/456k [00:00<00:00, 1.79MiB/s]\n"
      ]
     }
    ],
@@ -1852,7 +1852,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 34,
    "id": "Csbr60to50FL",
    "metadata": {
     "id": "Csbr60to50FL"
@@ -1908,7 +1908,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 35,
    "id": "bcc7bc04-6aa6-4516-a147-460e2f466eab",
    "metadata": {},
    "outputs": [],
@@ -1933,7 +1933,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 36,
    "id": "X7kU3aAj7vTJ",
    "metadata": {
     "colab": {
@@ -1965,7 +1965,7 @@
       "Ep 5 (Step 000550): Train loss 0.207, Val loss 0.143\n",
       "Ep 5 (Step 000600): Train loss 0.083, Val loss 0.074\n",
       "Training accuracy: 100.00% | Validation accuracy: 97.50%\n",
-      "Training completed in 5.65 minutes.\n"
+      "Training completed in 5.38 minutes.\n"
      ]
     }
    ],
@@ -1999,7 +1999,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 37,
    "id": "cURgnDqdCeka",
    "metadata": {
     "id": "cURgnDqdCeka"
@@ -2030,7 +2030,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 38,
    "id": "OIqRt466DiGk",
    "metadata": {
     "colab": {
@@ -2043,7 +2043,7 @@
    "outputs": [
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 500x300 with 2 Axes>"
       ]
@@ -2071,7 +2071,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 39,
    "id": "yz8BIsaF0TUo",
    "metadata": {
     "colab": {
@@ -2084,7 +2084,7 @@
    "outputs": [
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 500x300 with 2 Axes>"
       ]
@@ -2112,7 +2112,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 40,
    "id": "UHWaJFrjY0zW",
    "metadata": {
     "colab": {
@@ -2180,7 +2180,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 41,
    "id": "aHdn6xvL-IW5",
    "metadata": {
     "id": "aHdn6xvL-IW5"
@@ -2220,7 +2220,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 42,
    "id": "apU_pf51AWSV",
    "metadata": {
     "colab": {
@@ -2251,7 +2251,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": 43,
    "id": "1g5VTOo_Ajs5",
    "metadata": {
     "colab": {
@@ -2290,7 +2290,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 41,
+   "execution_count": 44,
    "id": "mYnX-gI1CfQY",
    "metadata": {
     "id": "mYnX-gI1CfQY"
@@ -2310,7 +2310,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 45,
    "id": "cc4e68a5-d492-493b-87ef-45c475f353f5",
    "metadata": {},
    "outputs": [
@@ -2320,13 +2320,13 @@
        "<All keys matched successfully>"
       ]
      },
-     "execution_count": 42,
+     "execution_count": 45,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "model_state_dict = torch.load(\"review_classifier.pth\", map_location=device)\n",
+    "model_state_dict = torch.load(\"review_classifier.pth\", map_location=device, weights_only=True)\n",
     "model.load_state_dict(model_state_dict)"
    ]
   },
@@ -2372,7 +2372,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.2"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,
diff --git a/ch06/01_main-chapter-code/load-finetuned-model.ipynb b/ch06/01_main-chapter-code/load-finetuned-model.ipynb
index 440476f..7ac6f5e 100644
--- a/ch06/01_main-chapter-code/load-finetuned-model.ipynb
+++ b/ch06/01_main-chapter-code/load-finetuned-model.ipynb
@@ -46,8 +46,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "tiktoken version: 0.6.0\n",
-      "torch version: 2.2.2\n"
+      "tiktoken version: 0.7.0\n",
+      "torch version: 2.4.0\n"
      ]
     }
    ],
@@ -127,7 +127,7 @@
     "\n",
     "# Then load pretrained weights\n",
     "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
-    "model.load_state_dict(torch.load(\"review_classifier.pth\", map_location=device))\n",
+    "model.load_state_dict(torch.load(\"review_classifier.pth\", map_location=device, weights_only=True))\n",
     "model.eval();"
    ]
   },
@@ -241,7 +241,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.2"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,
diff --git a/ch07/01_main-chapter-code/ch07.ipynb b/ch07/01_main-chapter-code/ch07.ipynb
index 004c55e..529d1f2 100644
--- a/ch07/01_main-chapter-code/ch07.ipynb
+++ b/ch07/01_main-chapter-code/ch07.ipynb
@@ -41,18 +41,18 @@
      "base_uri": "https://localhost:8080/"
     },
     "id": "4e19327b-6c02-4881-ad02-9b6d3ec0b1b4",
-    "outputId": "2bdd4d05-3aa3-4b7e-c478-6a210e8ff722"
+    "outputId": "9d937b84-d8f8-4ce9-cc3c-211188f49a10"
    },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "matplotlib version: 3.9.0\n",
+      "matplotlib version: 3.7.1\n",
       "tiktoken version: 0.7.0\n",
-      "torch version: 2.3.1\n",
+      "torch version: 2.4.0\n",
       "tqdm version: 4.66.4\n",
-      "tensorflow version: 2.16.1\n"
+      "tensorflow version: 2.15.0\n"
      ]
     }
    ],
@@ -153,7 +153,7 @@
      "base_uri": "https://localhost:8080/"
     },
     "id": "0G3axLw6kY1N",
-    "outputId": "e742b203-78e8-44f4-edbc-8dcaeba3fc5e"
+    "outputId": "a5f70eb8-6248-4834-e7ae-6105e94e5afa"
    },
    "outputs": [
     {
@@ -216,7 +216,7 @@
      "base_uri": "https://localhost:8080/"
     },
     "id": "-LiuBMsHkzQV",
-    "outputId": "535ddaef-ddc8-4a40-96d2-12d7414838b1"
+    "outputId": "cc742019-b8d7-40f9-b21a-6a5ddf821377"
    },
    "outputs": [
     {
@@ -244,14 +244,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "id": "uFInFxDDk2Je",
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "uFInFxDDk2Je",
-    "outputId": "01c760fd-53d6-4d94-997d-f72c6675c64e"
+    "outputId": "70241295-a9ec-4b7d-caf5-ab6f267e3271"
    },
    "outputs": [
     {
@@ -301,7 +301,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "id": "Jhk37nnJnkBh",
    "metadata": {
     "id": "Jhk37nnJnkBh"
@@ -332,14 +332,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "id": "F9UQRfjzo4Js",
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "F9UQRfjzo4Js",
-    "outputId": "47ae5684-c906-41bd-a3ea-e1504f861fd1"
+    "outputId": "13ec7abf-ad94-4e26-860d-6a39a344f31f"
    },
    "outputs": [
     {
@@ -378,14 +378,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "id": "a3891fa9-f738-41cd-946c-80ef9a99c346",
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "a3891fa9-f738-41cd-946c-80ef9a99c346",
-    "outputId": "4630975d-9f2e-448a-a899-2f54bdf4a114"
+    "outputId": "d6be5713-1293-4a70-c8c8-a86ea8e95817"
    },
    "outputs": [
     {
@@ -421,7 +421,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 8,
    "id": "aFZVopbIlNfx",
    "metadata": {
     "id": "aFZVopbIlNfx"
@@ -439,14 +439,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 9,
    "id": "-zf6oht6bIUQ",
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "-zf6oht6bIUQ",
-    "outputId": "16807a14-8a76-4710-e05d-9b770718d53d"
+    "outputId": "bb5fe8e5-1ce5-4fca-a430-76ecf42e99ef"
    },
    "outputs": [
     {
@@ -511,7 +511,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 10,
    "id": "adc29dc4-f1c7-4c71-937b-95119d6239bb",
    "metadata": {
     "id": "adc29dc4-f1c7-4c71-937b-95119d6239bb"
@@ -556,14 +556,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 11,
    "id": "ff24fe1a-5746-461c-ad3d-b6d84a1a7c96",
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "ff24fe1a-5746-461c-ad3d-b6d84a1a7c96",
-    "outputId": "5a7a4a95-4b2b-46a9-d15d-4787edb66849"
+    "outputId": "4d63f8b8-b4ad-45d9-9e93-c9dd8c2b7706"
    },
    "outputs": [
     {
@@ -605,7 +605,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 12,
    "id": "eb4c77dd-c956-4a1b-897b-b466909f18ca",
    "metadata": {
     "id": "eb4c77dd-c956-4a1b-897b-b466909f18ca"
@@ -631,10 +631,10 @@
     "        new_item += [pad_token_id]\n",
     "        # Pad sequences to batch_max_length\n",
     "        padded = (\n",
-    "            new_item + [pad_token_id] * \n",
+    "            new_item + [pad_token_id] *\n",
     "            (batch_max_length - len(new_item))\n",
     "        )\n",
-    "        # Via padded[:-1], we remove the extra padded token \n",
+    "        # Via padded[:-1], we remove the extra padded token\n",
     "        # that has been added via the +1 setting in batch_max_length\n",
     "        # (the extra padding token will be relevant in later codes)\n",
     "        inputs = torch.tensor(padded[:-1])\n",
@@ -647,14 +647,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 13,
    "id": "8fb02373-59b3-4f3a-b1d1-8181a2432645",
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "8fb02373-59b3-4f3a-b1d1-8181a2432645",
-    "outputId": "02a1ba16-dad1-49e8-b5e0-582593da6084"
+    "outputId": "8705ca9a-e999-4f70-9db8-1ad084eba7bb"
    },
    "outputs": [
     {
@@ -738,7 +738,7 @@
     "        new_item += [pad_token_id]\n",
     "        # Pad sequences to max_length\n",
     "        padded = (\n",
-    "            new_item + [pad_token_id] * \n",
+    "            new_item + [pad_token_id] *\n",
     "            (batch_max_length - len(new_item))\n",
     "        )\n",
     "        inputs = torch.tensor(padded[:-1])  # Truncate the last token for inputs\n",
@@ -761,7 +761,7 @@
      "base_uri": "https://localhost:8080/"
     },
     "id": "6eb2bce3-28a7-4f39-9d4b-5e972d69066c",
-    "outputId": "7fd85f5b-a00f-47ae-bd71-34f0fdef38a4"
+    "outputId": "b9ceae14-13c2-49f7-f4a4-b503f3db3009"
    },
    "outputs": [
     {
@@ -845,7 +845,7 @@
     "        new_item += [pad_token_id]\n",
     "        # Pad sequences to max_length\n",
     "        padded = (\n",
-    "            new_item + [pad_token_id] * \n",
+    "            new_item + [pad_token_id] *\n",
     "            (batch_max_length - len(new_item))\n",
     "        )\n",
     "        inputs = torch.tensor(padded[:-1])  # Truncate the last token for inputs\n",
@@ -881,7 +881,7 @@
      "base_uri": "https://localhost:8080/"
     },
     "id": "cdf5eec4-9ebe-4be0-9fca-9a47bee88fdc",
-    "outputId": "a0e6f58c-5bb5-4d9d-87ca-0df9dd4b4748"
+    "outputId": "a5501547-239d-431d-fb04-da7fa2ffad79"
    },
    "outputs": [
     {
@@ -924,7 +924,7 @@
      "base_uri": "https://localhost:8080/"
     },
     "id": "W2jvh-OP9MFV",
-    "outputId": "9936e6bf-0498-4026-ee4d-70c93c9311a8"
+    "outputId": "b5cd858e-7c58-4a21-c5a7-e72768bd301c"
    },
    "outputs": [
     {
@@ -966,7 +966,7 @@
      "base_uri": "https://localhost:8080/"
     },
     "id": "nvVMuil89v9N",
-    "outputId": "6267fc1d-2075-4c13-efcd-1bf35ca3fc1c"
+    "outputId": "e4a07b99-a23c-4404-ccdb-5f93c39f3b09"
    },
    "outputs": [
     {
@@ -1008,7 +1008,7 @@
      "base_uri": "https://localhost:8080/"
     },
     "id": "RTyB1vah9p56",
-    "outputId": "a8f8e6eb-bb0d-4cdf-b7de-68664581d161"
+    "outputId": "28c16387-1d9c-48a7-eda7-aa270864683d"
    },
    "outputs": [
     {
@@ -1111,7 +1111,7 @@
      "base_uri": "https://localhost:8080/"
     },
     "id": "etpqqWh8phKc",
-    "outputId": "bd1a573e-7a9b-4659-c5ea-0787945c1c25"
+    "outputId": "925faf3a-6df4-4ad0-f276-f328493619c3"
    },
    "outputs": [
     {
@@ -1241,7 +1241,7 @@
      "base_uri": "https://localhost:8080/"
     },
     "id": "GGs1AI3vHpnX",
-    "outputId": "e9122e9d-c38d-4ac8-e29d-c3c11a15b93c"
+    "outputId": "53a9695d-87cb-4d7c-8b43-1561dfa68ba0"
    },
    "outputs": [
     {
@@ -1394,7 +1394,7 @@
      "base_uri": "https://localhost:8080/"
     },
     "id": "21b8fd02-014f-4481-9b71-5bfee8f9dfcd",
-    "outputId": "c3c8685e-ea95-4339-8f99-bda4a7043d94"
+    "outputId": "ce919ecd-5ded-453c-a312-10cf55c13da7"
    },
    "outputs": [
     {
@@ -1435,7 +1435,7 @@
      "base_uri": "https://localhost:8080/"
     },
     "id": "51649ab4-1a7e-4a9e-92c5-950a24fde211",
-    "outputId": "daae5192-4d88-40eb-d3d9-79ae510e3f26"
+    "outputId": "fdf486f3-e99d-4891-9814-afc9e4991020"
    },
    "outputs": [
     {
@@ -1506,27 +1506,27 @@
      "base_uri": "https://localhost:8080/"
     },
     "id": "0d249d67-5eba-414e-9bd2-972ebf01329d",
-    "outputId": "d58ae26d-ff8f-4c66-bc84-e1ae3429ce51"
+    "outputId": "3f08f5e1-ca7c-406d-e2ae-1b5fcafad3f2"
    },
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "2024-06-23 13:32:49.758022: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
-      "2024-06-23 13:32:49.811280: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
-      "2024-06-23 13:32:49.811317: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
-      "2024-06-23 13:32:49.813171: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
-      "2024-06-23 13:32:49.822198: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
+      "2024-07-25 02:22:49.969483: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
+      "2024-07-25 02:22:50.023103: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
+      "2024-07-25 02:22:50.023136: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
+      "2024-07-25 02:22:50.024611: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
+      "2024-07-25 02:22:50.033304: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
       "To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
-      "2024-06-23 13:32:51.049899: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n",
-      "checkpoint: 100%|██████████| 77.0/77.0 [00:00<00:00, 172kiB/s]\n",
-      "encoder.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 4.42MiB/s]\n",
-      "hparams.json: 100%|██████████| 91.0/91.0 [00:00<00:00, 165kiB/s]\n",
-      "model.ckpt.data-00000-of-00001: 100%|██████████| 1.42G/1.42G [00:23<00:00, 61.5MiB/s]\n",
-      "model.ckpt.index: 100%|██████████| 10.4k/10.4k [00:00<00:00, 15.3MiB/s]\n",
-      "model.ckpt.meta: 100%|██████████| 927k/927k [00:00<00:00, 4.75MiB/s]\n",
-      "vocab.bpe: 100%|██████████| 456k/456k [00:00<00:00, 3.54MiB/s]\n"
+      "2024-07-25 02:22:51.282247: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n",
+      "checkpoint: 100%|██████████| 77.0/77.0 [00:00<00:00, 169kiB/s]\n",
+      "encoder.json: 100%|██████████| 1.04M/1.04M [00:00<00:00, 2.43MiB/s]\n",
+      "hparams.json: 100%|██████████| 91.0/91.0 [00:00<00:00, 168kiB/s]\n",
+      "model.ckpt.data-00000-of-00001: 100%|██████████| 1.42G/1.42G [00:56<00:00, 25.0MiB/s]\n",
+      "model.ckpt.index: 100%|██████████| 10.4k/10.4k [00:00<00:00, 16.5MiB/s]\n",
+      "model.ckpt.meta: 100%|██████████| 927k/927k [00:00<00:00, 1.96MiB/s]\n",
+      "vocab.bpe: 100%|██████████| 456k/456k [00:00<00:00, 1.53MiB/s]\n"
      ]
     }
    ],
@@ -1555,7 +1555,7 @@
     "\n",
     "model_size = CHOOSE_MODEL.split(\" \")[-1].lstrip(\"(\").rstrip(\")\")\n",
     "settings, params = download_and_load_gpt2(\n",
-    "    model_size=model_size, \n",
+    "    model_size=model_size,\n",
     "    models_dir=\"gpt2\"\n",
     ")\n",
     "\n",
@@ -1583,7 +1583,7 @@
      "base_uri": "https://localhost:8080/"
     },
     "id": "7bd32b7c-5b44-4d25-a09f-46836802ca74",
-    "outputId": "6dcedbe5-5c9c-4d5a-8524-6346b3185b97"
+    "outputId": "30d4fbd9-7d22-4545-cfc5-c5749cc0bd93"
    },
    "outputs": [
     {
@@ -1649,15 +1649,13 @@
      "base_uri": "https://localhost:8080/"
     },
     "id": "ba4a55bf-a245-48d8-beda-2838a58fb5ba",
-    "outputId": "9c1921a3-becc-4a30-c899-ce039c3fdcf2"
+    "outputId": "b46de9b3-98f0-45e4-a9ae-86870c3244a1"
    },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "### Response:\n",
-      "\n",
       "The chef cooks the meal every day.\n",
       "\n",
       "### Instruction:\n",
@@ -1743,15 +1741,15 @@
      "base_uri": "https://localhost:8080/"
     },
     "id": "d99fc6f8-63b2-43da-adbb-a7b6b92c8dd5",
-    "outputId": "1ceb796a-b615-46b4-f1f0-661b6d53f9fb"
+    "outputId": "36fdf03b-6fa6-46c3-c77d-ecc99e886265"
    },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Training loss: 3.825908660888672\n",
-      "Validation loss: 3.7619335651397705\n"
+      "Training loss: 3.82590970993042\n",
+      "Validation loss: 3.761933755874634\n"
      ]
     }
    ],
@@ -1813,7 +1811,7 @@
      "base_uri": "https://localhost:8080/"
     },
     "id": "78bcf83a-1fff-4540-97c1-765c4016d5e3",
-    "outputId": "f978a643-6307-4e30-9fdc-66d9db978fa1"
+    "outputId": "cea0618c-56ca-418a-c972-bcc060362727"
    },
    "outputs": [
     {
@@ -1821,55 +1819,55 @@
      "output_type": "stream",
      "text": [
       "Ep 1 (Step 000000): Train loss 2.637, Val loss 2.626\n",
-      "Ep 1 (Step 000005): Train loss 1.174, Val loss 1.103\n",
+      "Ep 1 (Step 000005): Train loss 1.174, Val loss 1.102\n",
       "Ep 1 (Step 000010): Train loss 0.872, Val loss 0.944\n",
       "Ep 1 (Step 000015): Train loss 0.857, Val loss 0.906\n",
       "Ep 1 (Step 000020): Train loss 0.776, Val loss 0.881\n",
       "Ep 1 (Step 000025): Train loss 0.754, Val loss 0.859\n",
-      "Ep 1 (Step 000030): Train loss 0.800, Val loss 0.836\n",
-      "Ep 1 (Step 000035): Train loss 0.714, Val loss 0.809\n",
+      "Ep 1 (Step 000030): Train loss 0.799, Val loss 0.836\n",
+      "Ep 1 (Step 000035): Train loss 0.714, Val loss 0.808\n",
       "Ep 1 (Step 000040): Train loss 0.672, Val loss 0.806\n",
       "Ep 1 (Step 000045): Train loss 0.633, Val loss 0.789\n",
-      "Ep 1 (Step 000050): Train loss 0.663, Val loss 0.782\n",
+      "Ep 1 (Step 000050): Train loss 0.663, Val loss 0.783\n",
       "Ep 1 (Step 000055): Train loss 0.760, Val loss 0.763\n",
       "Ep 1 (Step 000060): Train loss 0.719, Val loss 0.743\n",
       "Ep 1 (Step 000065): Train loss 0.653, Val loss 0.735\n",
-      "Ep 1 (Step 000070): Train loss 0.535, Val loss 0.732\n",
-      "Ep 1 (Step 000075): Train loss 0.568, Val loss 0.738\n",
-      "Ep 1 (Step 000080): Train loss 0.603, Val loss 0.733\n",
-      "Ep 1 (Step 000085): Train loss 0.515, Val loss 0.716\n",
-      "Ep 1 (Step 000090): Train loss 0.573, Val loss 0.698\n",
-      "Ep 1 (Step 000095): Train loss 0.505, Val loss 0.688\n",
-      "Ep 1 (Step 000100): Train loss 0.507, Val loss 0.683\n",
-      "Ep 1 (Step 000105): Train loss 0.568, Val loss 0.675\n",
-      "Ep 1 (Step 000110): Train loss 0.562, Val loss 0.670\n",
-      "Ep 1 (Step 000115): Train loss 0.520, Val loss 0.665\n",
+      "Ep 1 (Step 000070): Train loss 0.532, Val loss 0.729\n",
+      "Ep 1 (Step 000075): Train loss 0.569, Val loss 0.728\n",
+      "Ep 1 (Step 000080): Train loss 0.605, Val loss 0.725\n",
+      "Ep 1 (Step 000085): Train loss 0.509, Val loss 0.709\n",
+      "Ep 1 (Step 000090): Train loss 0.562, Val loss 0.691\n",
+      "Ep 1 (Step 000095): Train loss 0.500, Val loss 0.681\n",
+      "Ep 1 (Step 000100): Train loss 0.503, Val loss 0.677\n",
+      "Ep 1 (Step 000105): Train loss 0.564, Val loss 0.670\n",
+      "Ep 1 (Step 000110): Train loss 0.555, Val loss 0.666\n",
+      "Ep 1 (Step 000115): Train loss 0.508, Val loss 0.664\n",
       "Below is an instruction that describes a task. Write a response that appropriately completes the request.  ### Instruction: Convert the active sentence to passive: 'The chef cooks the meal every day.'  ### Response: The meal is prepared every day by the chef.<|endoftext|>The following is an instruction that describes a task. Write a response that appropriately completes the request.  ### Instruction: Convert the active sentence to passive:\n",
-      "Ep 2 (Step 000120): Train loss 0.438, Val loss 0.670\n",
-      "Ep 2 (Step 000125): Train loss 0.453, Val loss 0.685\n",
-      "Ep 2 (Step 000130): Train loss 0.448, Val loss 0.681\n",
-      "Ep 2 (Step 000135): Train loss 0.408, Val loss 0.677\n",
-      "Ep 2 (Step 000140): Train loss 0.409, Val loss 0.676\n",
-      "Ep 2 (Step 000145): Train loss 0.373, Val loss 0.676\n",
-      "Ep 2 (Step 000150): Train loss 0.381, Val loss 0.674\n",
-      "Ep 2 (Step 000155): Train loss 0.421, Val loss 0.677\n",
-      "Ep 2 (Step 000160): Train loss 0.416, Val loss 0.686\n",
-      "Ep 2 (Step 000165): Train loss 0.381, Val loss 0.688\n",
-      "Ep 2 (Step 000170): Train loss 0.329, Val loss 0.679\n",
+      "Ep 2 (Step 000120): Train loss 0.435, Val loss 0.672\n",
+      "Ep 2 (Step 000125): Train loss 0.451, Val loss 0.687\n",
+      "Ep 2 (Step 000130): Train loss 0.447, Val loss 0.683\n",
+      "Ep 2 (Step 000135): Train loss 0.405, Val loss 0.682\n",
+      "Ep 2 (Step 000140): Train loss 0.409, Val loss 0.681\n",
+      "Ep 2 (Step 000145): Train loss 0.369, Val loss 0.680\n",
+      "Ep 2 (Step 000150): Train loss 0.382, Val loss 0.675\n",
+      "Ep 2 (Step 000155): Train loss 0.413, Val loss 0.675\n",
+      "Ep 2 (Step 000160): Train loss 0.415, Val loss 0.683\n",
+      "Ep 2 (Step 000165): Train loss 0.379, Val loss 0.686\n",
+      "Ep 2 (Step 000170): Train loss 0.323, Val loss 0.681\n",
       "Ep 2 (Step 000175): Train loss 0.337, Val loss 0.669\n",
-      "Ep 2 (Step 000180): Train loss 0.393, Val loss 0.657\n",
-      "Ep 2 (Step 000185): Train loss 0.420, Val loss 0.659\n",
-      "Ep 2 (Step 000190): Train loss 0.342, Val loss 0.651\n",
-      "Ep 2 (Step 000195): Train loss 0.328, Val loss 0.636\n",
-      "Ep 2 (Step 000200): Train loss 0.312, Val loss 0.635\n",
-      "Ep 2 (Step 000205): Train loss 0.353, Val loss 0.633\n",
-      "Ep 2 (Step 000210): Train loss 0.368, Val loss 0.634\n",
-      "Ep 2 (Step 000215): Train loss 0.395, Val loss 0.639\n",
-      "Ep 2 (Step 000220): Train loss 0.301, Val loss 0.652\n",
-      "Ep 2 (Step 000225): Train loss 0.350, Val loss 0.664\n",
-      "Ep 2 (Step 000230): Train loss 0.300, Val loss 0.657\n",
+      "Ep 2 (Step 000180): Train loss 0.392, Val loss 0.656\n",
+      "Ep 2 (Step 000185): Train loss 0.415, Val loss 0.657\n",
+      "Ep 2 (Step 000190): Train loss 0.340, Val loss 0.648\n",
+      "Ep 2 (Step 000195): Train loss 0.330, Val loss 0.634\n",
+      "Ep 2 (Step 000200): Train loss 0.310, Val loss 0.634\n",
+      "Ep 2 (Step 000205): Train loss 0.352, Val loss 0.630\n",
+      "Ep 2 (Step 000210): Train loss 0.367, Val loss 0.630\n",
+      "Ep 2 (Step 000215): Train loss 0.394, Val loss 0.635\n",
+      "Ep 2 (Step 000220): Train loss 0.299, Val loss 0.648\n",
+      "Ep 2 (Step 000225): Train loss 0.346, Val loss 0.661\n",
+      "Ep 2 (Step 000230): Train loss 0.292, Val loss 0.659\n",
       "Below is an instruction that describes a task. Write a response that appropriately completes the request.  ### Instruction: Convert the active sentence to passive: 'The chef cooks the meal every day.'  ### Response: The meal is cooked every day by the chef.<|endoftext|>The following is an instruction that describes a task. Write a response that appropriately completes the request.  ### Instruction: What is the capital of the United Kingdom\n",
-      "Training completed in 0.88 minutes.\n"
+      "Training completed in 1.84 minutes.\n"
      ]
     }
    ],
@@ -1917,12 +1915,12 @@
      "height": 308
     },
     "id": "4acd368b-1403-4807-a218-9102e35bfdbb",
-    "outputId": "026a0b78-fd64-45b5-aafe-09309f7e180c"
+    "outputId": "680da58a-9bd7-402d-ac95-470a4a29a6c4"
    },
    "outputs": [
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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\n",
       "text/plain": [
        "<Figure size 500x300 with 2 Axes>"
       ]
@@ -1983,14 +1981,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 36,
    "id": "VQ2NZMbfucAc",
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "VQ2NZMbfucAc",
-    "outputId": "6f376ffe-c059-4c15-905b-bf408f2a86f8"
+    "outputId": "8416b4ac-1993-4628-dea6-7789cdc8926c"
    },
    "outputs": [
     {
@@ -2086,21 +2084,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 37,
    "id": "-PNGKzY4snKP",
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "-PNGKzY4snKP",
-    "outputId": "4b631b9c-73bf-4cdd-dc78-ddcd3a03f934"
+    "outputId": "0453dfb3-51cd-49e2-9e63-f65b606c3478"
    },
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 110/110 [01:05<00:00,  1.68it/s]\n"
+      "100%|██████████| 110/110 [01:11<00:00,  1.54it/s]\n"
      ]
     }
    ],
@@ -2140,14 +2138,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 38,
    "id": "u-AvCCMTnPSE",
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "u-AvCCMTnPSE",
-    "outputId": "bad28133-b088-4cdf-8056-68159268a48e"
+    "outputId": "ce3b2545-8990-4446-e44c-a945e0049c06"
    },
    "outputs": [
     {
@@ -2174,14 +2172,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 39,
    "id": "8cBU0iHmVfOI",
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "8cBU0iHmVfOI",
-    "outputId": "860a2d06-2d0e-4ae8-943d-dd12d299eed9",
+    "outputId": "d6e7f226-9310-43f5-f31f-adc3a893a8e9",
     "scrolled": true
    },
    "outputs": [
@@ -2339,7 +2337,7 @@
      "height": 193
     },
     "id": "026e8570-071e-48a2-aa38-64d7be35f288",
-    "outputId": "c0f1d14f-d545-4605-a1ee-0f1eacd98cf6"
+    "outputId": "e30d3533-e1f5-4aa9-b24f-33273fc7b30e"
    },
    "outputs": [
     {
@@ -2417,8 +2415,7 @@
    "execution_count": 3,
    "id": "e3ae0e10-2b28-42ce-8ea2-d9366a58088f",
    "metadata": {
-    "id": "e3ae0e10-2b28-42ce-8ea2-d9366a58088f",
-    "outputId": "f94eb862-b9b6-4ece-f4b0-28be5d1c8e3e"
+    "id": "e3ae0e10-2b28-42ce-8ea2-d9366a58088f"
    },
    "outputs": [
     {
@@ -2447,8 +2444,8 @@
     "import urllib.request\n",
     "\n",
     "def query_model(\n",
-    "    prompt, \n",
-    "    model=\"llama3\", \n",
+    "    prompt,\n",
+    "    model=\"llama3\",\n",
     "    url=\"http://localhost:11434/api/chat\"\n",
     "):\n",
     "    # Create the data payload as a dictionary\n",
@@ -2470,8 +2467,8 @@
     "\n",
     "    # Create a request object, setting the method to POST and adding necessary headers\n",
     "    request = urllib.request.Request(\n",
-    "        url, \n",
-    "        data=payload, \n",
+    "        url,\n",
+    "        data=payload,\n",
     "        method=\"POST\"\n",
     "    )\n",
     "    request.add_header(\"Content-Type\", \"application/json\")\n",
@@ -2510,8 +2507,7 @@
    "execution_count": 4,
    "id": "86b839d4-064d-4178-b2d7-01691b452e5e",
    "metadata": {
-    "id": "86b839d4-064d-4178-b2d7-01691b452e5e",
-    "outputId": "e68f60c1-5f23-4da5-887a-757e777de616"
+    "id": "86b839d4-064d-4178-b2d7-01691b452e5e"
    },
    "outputs": [
     {
@@ -2612,15 +2608,14 @@
    "execution_count": 5,
    "id": "9d7bca69-97c4-47a5-9aa0-32f116fa37eb",
    "metadata": {
-    "id": "9d7bca69-97c4-47a5-9aa0-32f116fa37eb",
-    "outputId": "d5d5f27f-f57e-46e9-dd5c-d9d9c483692c"
+    "id": "9d7bca69-97c4-47a5-9aa0-32f116fa37eb"
    },
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Scoring entries: 100%|████████████████████████| 110/110 [01:08<00:00,  1.60it/s]"
+      "Scoring entries: 100%|████████████████████████| 110/110 [01:10<00:00,  1.57it/s]"
      ]
     },
     {
@@ -2750,7 +2745,6 @@
   "accelerator": "GPU",
   "colab": {
    "gpuType": "A100",
-   "machine_shape": "hm",
    "provenance": []
   },
   "kernelspec": {
diff --git a/ch07/01_main-chapter-code/load-finetuned-model.ipynb b/ch07/01_main-chapter-code/load-finetuned-model.ipynb
index f9193fb..8420841 100644
--- a/ch07/01_main-chapter-code/load-finetuned-model.ipynb
+++ b/ch07/01_main-chapter-code/load-finetuned-model.ipynb
@@ -47,7 +47,7 @@
      "output_type": "stream",
      "text": [
       "tiktoken version: 0.7.0\n",
-      "torch version: 2.3.1\n"
+      "torch version: 2.4.0\n"
      ]
     }
    ],
@@ -120,7 +120,11 @@
    "source": [
     "import torch\n",
     "\n",
-    "model.load_state_dict(torch.load(\"gpt2-medium355M-sft.pth\", map_location=torch.device(\"cpu\")))\n",
+    "model.load_state_dict(torch.load(\n",
+    "    \"gpt2-medium355M-sft.pth\",\n",
+    "    map_location=torch.device(\"cpu\"),\n",
+    "    weights_only=True\n",
+    "))\n",
     "model.eval();"
    ]
   },
@@ -207,7 +211,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.2"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,