formatting for consistency with production chapter

ch02/01_main-chapter-code/ch02.ipynb

@@ -153,6 +153,24 @@
   {
    "cell_type": "code",
    "execution_count": 2,
+   "id": "40f9d9b1-6d32-485a-825a-a95392a86d79",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import urllib.request\n",
+    "\n",
+    "if not os.path.exists(\"the-verdict.txt\"):\n",
+    "    url = (\"https://raw.githubusercontent.com/rasbt/\"\n",
+    "           \"LLMs-from-scratch/main/ch02/01_main-chapter-code/\"\n",
+    "           \"the-verdict.txt\")\n",
+    "    file_path = \"the-verdict.txt\"\n",
+    "    urllib.request.urlretrieve(url, file_path)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
    "id": "8a769e87-470a-48b9-8bdb-12841b416198",
    "metadata": {},
    "outputs": [
@@ -185,7 +203,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "id": "737dd5b0-9dbb-4a97-9ae4-3482c8c04be7",
    "metadata": {},
    "outputs": [
@@ -216,7 +234,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "id": "ea02489d-01f9-4247-b7dd-a0d63f62ef07",
    "metadata": {},
    "outputs": [
@@ -244,7 +262,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "4d8a6fb7-2e62-4a12-ad06-ccb04f25fed7",
    "metadata": {},
    "outputs": [
@@ -272,7 +290,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "id": "ed3a9467-04b4-49d9-96c5-b8042bcf8374",
    "metadata": {},
    "outputs": [
@@ -310,7 +328,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "id": "8c567caa-8ff5-49a8-a5cc-d365b0a78a99",
    "metadata": {},
    "outputs": [
@@ -338,7 +356,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "id": "35db7b5e-510b-4c45-995f-f5ad64a8e19c",
    "metadata": {},
    "outputs": [
@@ -388,7 +406,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 10,
    "id": "7fdf0533-5ab6-42a5-83fa-a3b045de6396",
    "metadata": {},
    "outputs": [
@@ -409,7 +427,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 11,
    "id": "77d00d96-881f-4691-bb03-84fec2a75a26",
    "metadata": {},
    "outputs": [],
@@ -427,7 +445,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 12,
    "id": "e1c5de4a-aa4e-4aec-b532-10bb364039d6",
    "metadata": {},
    "outputs": [
@@ -522,7 +540,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 13,
    "id": "f531bf46-7c25-4ef8-bff8-0d27518676d5",
    "metadata": {},
    "outputs": [],
@@ -534,7 +552,9 @@
     "    \n",
     "    def encode(self, text):\n",
     "        preprocessed = re.split(r'([,.?_!\"()\\']|--|\\s)', text)\n",
-    "        preprocessed = [item.strip() for item in preprocessed if item.strip()]\n",
+    "        preprocessed = [\n",
+    "            item.strip() for item in preprocessed if item.strip()\n",
+    "        ]\n",
     "        ids = [self.str_to_int[s] for s in preprocessed]\n",
     "        return ids\n",
     "        \n",
@@ -573,7 +593,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 14,
    "id": "647364ec-7995-4654-9b4a-7607ccf5f1e4",
    "metadata": {},
    "outputs": [
@@ -588,7 +608,8 @@
    "source": [
     "tokenizer = SimpleTokenizerV1(vocab)\n",
     "\n",
-    "text = \"\"\"\"It's the last he painted, you know,\" Mrs. Gisburn said with pardonable pride.\"\"\"\n",
+    "text = \"\"\"\"It's the last he painted, you know,\" \n",
+    "           Mrs. Gisburn said with pardonable pride.\"\"\"\n",
     "ids = tokenizer.encode(text)\n",
     "print(ids)"
    ]
@@ -603,7 +624,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 15,
    "id": "01d8c8fb-432d-4a49-b332-99f23b233746",
    "metadata": {},
    "outputs": [
@@ -613,7 +634,7 @@
        "'\" It\\' s the last he painted, you know,\" Mrs. Gisburn said with pardonable pride.'"
       ]
      },
-     "execution_count": 14,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -624,7 +645,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 16,
    "id": "54f6aa8b-9827-412e-9035-e827296ab0fe",
    "metadata": {},
    "outputs": [
@@ -634,7 +655,7 @@
        "'\" It\\' s the last he painted, you know,\" Mrs. Gisburn said with pardonable pride.'"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 16,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -712,7 +733,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 17,
    "id": "d5767eff-440c-4de1-9289-f789349d6b85",
    "metadata": {},
    "outputs": [
@@ -723,9 +744,9 @@
      "traceback": [
       "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
       "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[16], line 5\u001b[0m\n\u001b[1;32m      1\u001b[0m tokenizer \u001b[38;5;241m=\u001b[39m SimpleTokenizerV1(vocab)\n\u001b[1;32m      3\u001b[0m text \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mHello, do you like tea. Is this-- a test?\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m----> 5\u001b[0m \u001b[43mtokenizer\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mencode\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtext\u001b[49m\u001b[43m)\u001b[49m\n",
-      "Cell \u001b[0;32mIn[12], line 9\u001b[0m, in \u001b[0;36mSimpleTokenizerV1.encode\u001b[0;34m(self, text)\u001b[0m\n\u001b[1;32m      7\u001b[0m preprocessed \u001b[38;5;241m=\u001b[39m re\u001b[38;5;241m.\u001b[39msplit(\u001b[38;5;124mr\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m([,.?_!\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m()\u001b[39m\u001b[38;5;130;01m\\'\u001b[39;00m\u001b[38;5;124m]|--|\u001b[39m\u001b[38;5;124m\\\u001b[39m\u001b[38;5;124ms)\u001b[39m\u001b[38;5;124m'\u001b[39m, text)\n\u001b[1;32m      8\u001b[0m preprocessed \u001b[38;5;241m=\u001b[39m [item\u001b[38;5;241m.\u001b[39mstrip() \u001b[38;5;28;01mfor\u001b[39;00m item \u001b[38;5;129;01min\u001b[39;00m preprocessed \u001b[38;5;28;01mif\u001b[39;00m item\u001b[38;5;241m.\u001b[39mstrip()]\n\u001b[0;32m----> 9\u001b[0m ids \u001b[38;5;241m=\u001b[39m \u001b[43m[\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstr_to_int\u001b[49m\u001b[43m[\u001b[49m\u001b[43ms\u001b[49m\u001b[43m]\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43ms\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mpreprocessed\u001b[49m\u001b[43m]\u001b[49m\n\u001b[1;32m     10\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m ids\n",
-      "Cell \u001b[0;32mIn[12], line 9\u001b[0m, in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m      7\u001b[0m preprocessed \u001b[38;5;241m=\u001b[39m re\u001b[38;5;241m.\u001b[39msplit(\u001b[38;5;124mr\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m([,.?_!\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m()\u001b[39m\u001b[38;5;130;01m\\'\u001b[39;00m\u001b[38;5;124m]|--|\u001b[39m\u001b[38;5;124m\\\u001b[39m\u001b[38;5;124ms)\u001b[39m\u001b[38;5;124m'\u001b[39m, text)\n\u001b[1;32m      8\u001b[0m preprocessed \u001b[38;5;241m=\u001b[39m [item\u001b[38;5;241m.\u001b[39mstrip() \u001b[38;5;28;01mfor\u001b[39;00m item \u001b[38;5;129;01min\u001b[39;00m preprocessed \u001b[38;5;28;01mif\u001b[39;00m item\u001b[38;5;241m.\u001b[39mstrip()]\n\u001b[0;32m----> 9\u001b[0m ids \u001b[38;5;241m=\u001b[39m [\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstr_to_int\u001b[49m\u001b[43m[\u001b[49m\u001b[43ms\u001b[49m\u001b[43m]\u001b[49m \u001b[38;5;28;01mfor\u001b[39;00m s \u001b[38;5;129;01min\u001b[39;00m preprocessed]\n\u001b[1;32m     10\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m ids\n",
+      "Cell \u001b[0;32mIn[17], line 5\u001b[0m\n\u001b[1;32m      1\u001b[0m tokenizer \u001b[38;5;241m=\u001b[39m SimpleTokenizerV1(vocab)\n\u001b[1;32m      3\u001b[0m text \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mHello, do you like tea. Is this-- a test?\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m----> 5\u001b[0m \u001b[43mtokenizer\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mencode\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtext\u001b[49m\u001b[43m)\u001b[49m\n",
+      "Cell \u001b[0;32mIn[13], line 11\u001b[0m, in \u001b[0;36mSimpleTokenizerV1.encode\u001b[0;34m(self, text)\u001b[0m\n\u001b[1;32m      7\u001b[0m preprocessed \u001b[38;5;241m=\u001b[39m re\u001b[38;5;241m.\u001b[39msplit(\u001b[38;5;124mr\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m([,.?_!\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m()\u001b[39m\u001b[38;5;130;01m\\'\u001b[39;00m\u001b[38;5;124m]|--|\u001b[39m\u001b[38;5;124m\\\u001b[39m\u001b[38;5;124ms)\u001b[39m\u001b[38;5;124m'\u001b[39m, text)\n\u001b[1;32m      8\u001b[0m preprocessed \u001b[38;5;241m=\u001b[39m [\n\u001b[1;32m      9\u001b[0m     item\u001b[38;5;241m.\u001b[39mstrip() \u001b[38;5;28;01mfor\u001b[39;00m item \u001b[38;5;129;01min\u001b[39;00m preprocessed \u001b[38;5;28;01mif\u001b[39;00m item\u001b[38;5;241m.\u001b[39mstrip()\n\u001b[1;32m     10\u001b[0m ]\n\u001b[0;32m---> 11\u001b[0m ids \u001b[38;5;241m=\u001b[39m \u001b[43m[\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstr_to_int\u001b[49m\u001b[43m[\u001b[49m\u001b[43ms\u001b[49m\u001b[43m]\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43ms\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mpreprocessed\u001b[49m\u001b[43m]\u001b[49m\n\u001b[1;32m     12\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m ids\n",
+      "Cell \u001b[0;32mIn[13], line 11\u001b[0m, in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m      7\u001b[0m preprocessed \u001b[38;5;241m=\u001b[39m re\u001b[38;5;241m.\u001b[39msplit(\u001b[38;5;124mr\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m([,.?_!\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m()\u001b[39m\u001b[38;5;130;01m\\'\u001b[39;00m\u001b[38;5;124m]|--|\u001b[39m\u001b[38;5;124m\\\u001b[39m\u001b[38;5;124ms)\u001b[39m\u001b[38;5;124m'\u001b[39m, text)\n\u001b[1;32m      8\u001b[0m preprocessed \u001b[38;5;241m=\u001b[39m [\n\u001b[1;32m      9\u001b[0m     item\u001b[38;5;241m.\u001b[39mstrip() \u001b[38;5;28;01mfor\u001b[39;00m item \u001b[38;5;129;01min\u001b[39;00m preprocessed \u001b[38;5;28;01mif\u001b[39;00m item\u001b[38;5;241m.\u001b[39mstrip()\n\u001b[1;32m     10\u001b[0m ]\n\u001b[0;32m---> 11\u001b[0m ids \u001b[38;5;241m=\u001b[39m [\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mstr_to_int\u001b[49m\u001b[43m[\u001b[49m\u001b[43ms\u001b[49m\u001b[43m]\u001b[49m \u001b[38;5;28;01mfor\u001b[39;00m s \u001b[38;5;129;01min\u001b[39;00m preprocessed]\n\u001b[1;32m     12\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m ids\n",
       "\u001b[0;31mKeyError\u001b[0m: 'Hello'"
      ]
     }
@@ -750,7 +771,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 18,
    "id": "ce9df29c-6c5b-43f1-8c1a-c7f7b79db78f",
    "metadata": {},
    "outputs": [],
@@ -766,7 +787,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 19,
    "id": "57c3143b-e860-4d3b-a22a-de22b547a6a9",
    "metadata": {},
    "outputs": [
@@ -776,7 +797,7 @@
        "1161"
       ]
      },
-     "execution_count": 18,
+     "execution_count": 19,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -787,7 +808,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 20,
    "id": "50e51bb1-ae05-4aa8-a9ff-455b65ed1959",
    "metadata": {},
    "outputs": [
@@ -818,7 +839,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 21,
    "id": "948861c5-3f30-4712-a234-725f20d26f68",
    "metadata": {},
    "outputs": [],
@@ -831,8 +852,10 @@
     "    def encode(self, text):\n",
     "        preprocessed = re.split(r'([,.?_!\"()\\']|--|\\s)', text)\n",
     "        preprocessed = [item.strip() for item in preprocessed if item.strip()]\n",
-    "        preprocessed = [item if item in self.str_to_int \n",
-    "                        else \"<|unk|>\" for item in preprocessed]\n",
+    "        preprocessed = [\n",
+    "            item if item in self.str_to_int \n",
+    "            else \"<|unk|>\" for item in preprocessed\n",
+    "        ]\n",
     "\n",
     "        ids = [self.str_to_int[s] for s in preprocessed]\n",
     "        return ids\n",
@@ -854,7 +877,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 22,
    "id": "effcef79-e0a5-4f4a-a43a-31dd94b9250a",
    "metadata": {},
    "outputs": [
@@ -879,7 +902,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 23,
    "id": "ddfe7346-398d-4bf8-99f1-5b071244ce95",
    "metadata": {},
    "outputs": [
@@ -904,7 +927,7 @@
        " 7]"
       ]
      },
-     "execution_count": 22,
+     "execution_count": 23,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -915,7 +938,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 24,
    "id": "0c350ff6-2734-4e84-9ec7-d578baa4ae1b",
    "metadata": {},
    "outputs": [
@@ -925,7 +948,7 @@
        "'<|unk|>, do you like tea? <|endoftext|> In the sunlit terraces of the <|unk|>.'"
       ]
      },
-     "execution_count": 23,
+     "execution_count": 24,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -957,7 +980,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 25,
    "id": "ede1d41f-934b-4bf4-8184-54394a257a94",
    "metadata": {},
    "outputs": [],
@@ -967,7 +990,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 26,
    "id": "48967a77-7d17-42bf-9e92-fc619d63a59e",
    "metadata": {},
    "outputs": [
@@ -988,7 +1011,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 27,
    "id": "6ad3312f-a5f7-4efc-9d7d-8ea09d7b5128",
    "metadata": {},
    "outputs": [],
@@ -998,7 +1021,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 28,
    "id": "5ff2cd85-7cfb-4325-b390-219938589428",
    "metadata": {},
    "outputs": [
@@ -1006,12 +1029,15 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[15496, 11, 466, 345, 588, 8887, 30, 220, 50256, 554, 262, 4252, 18250, 8812, 2114, 286, 617, 34680, 27271, 13]\n"
+      "[15496, 11, 466, 345, 588, 8887, 30, 220, 50256, 554, 262, 4252, 18250, 8812, 2114, 1659, 617, 34680, 27271, 13]\n"
      ]
     }
    ],
    "source": [
-    "text = \"Hello, do you like tea? <|endoftext|> In the sunlit terraces of someunknownPlace.\"\n",
+    "text = (\n",
+    "    \"Hello, do you like tea? <|endoftext|> In the sunlit terraces\"\n",
+    "     \"of someunknownPlace.\"\n",
+    ")\n",
     "\n",
     "integers = tokenizer.encode(text, allowed_special={\"<|endoftext|>\"})\n",
     "\n",
@@ -1020,7 +1046,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 29,
    "id": "d26a48bb-f82e-41a8-a955-a1c9cf9d50ab",
    "metadata": {},
    "outputs": [
@@ -1028,7 +1054,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Hello, do you like tea? <|endoftext|> In the sunlit terraces of someunknownPlace.\n"
+      "Hello, do you like tea? <|endoftext|> In the sunlit terracesof someunknownPlace.\n"
      ]
     }
    ],
@@ -1080,7 +1106,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 30,
    "id": "848d5ade-fd1f-46c3-9e31-1426e315c71b",
    "metadata": {},
    "outputs": [
@@ -1111,7 +1137,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 31,
    "id": "e84424a7-646d-45b6-99e3-80d15fb761f2",
    "metadata": {},
    "outputs": [],
@@ -1121,7 +1147,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 32,
    "id": "dfbff852-a92f-48c8-a46d-143a0f109f40",
    "metadata": {},
    "outputs": [
@@ -1154,7 +1180,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 33,
    "id": "d97b031e-ed55-409d-95f2-aeb38c6fe366",
    "metadata": {},
    "outputs": [
@@ -1179,7 +1205,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 34,
    "id": "f57bd746-dcbf-4433-8e24-ee213a8c34a1",
    "metadata": {},
    "outputs": [
@@ -1221,7 +1247,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 35,
    "id": "e1770134-e7f3-4725-a679-e04c3be48cac",
    "metadata": {},
    "outputs": [
@@ -1258,7 +1284,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 36,
    "id": "74b41073-4c9f-46e2-a1bd-d38e4122b375",
    "metadata": {},
    "outputs": [],
@@ -1290,12 +1316,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 37,
    "id": "5eb30ebe-97b3-43c5-9ff1-a97d621b3c4e",
    "metadata": {},
    "outputs": [],
    "source": [
-    "def create_dataloader_v1(txt, batch_size=4, max_length=256, stride=128, shuffle=True, drop_last=True, num_workers=0):\n",
+    "def create_dataloader_v1(txt, batch_size=4, max_length=256, \n",
+    "                         stride=128, shuffle=True, drop_last=True,\n",
+    "                         num_workers=0):\n",
     "\n",
     "    # Initialize the tokenizer\n",
     "    tokenizer = tiktoken.get_encoding(\"gpt2\")\n",
@@ -1325,7 +1353,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 38,
    "id": "df31d96c-6bfd-4564-a956-6192242d7579",
    "metadata": {},
    "outputs": [],
@@ -1336,7 +1364,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 39,
    "id": "9226d00c-ad9a-4949-a6e4-9afccfc7214f",
    "metadata": {},
    "outputs": [
@@ -1349,7 +1377,9 @@
     }
    ],
    "source": [
-    "dataloader = create_dataloader_v1(raw_text, batch_size=1, max_length=4, stride=1, shuffle=False)\n",
+    "dataloader = create_dataloader_v1(\n",
+    "    raw_text, batch_size=1, max_length=4, stride=1, shuffle=False\n",
+    ")\n",
     "\n",
     "data_iter = iter(dataloader)\n",
     "first_batch = next(data_iter)\n",
@@ -1358,7 +1388,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 40,
    "id": "10deb4bc-4de1-4d20-921e-4b1c7a0e1a6d",
    "metadata": {},
    "outputs": [
@@ -1402,7 +1432,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": 41,
    "id": "1916e7a6-f03d-4f09-91a6-d0bdbac5a58c",
    "metadata": {},
    "outputs": [
@@ -1477,7 +1507,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 41,
+   "execution_count": 42,
    "id": "15a6304c-9474-4470-b85d-3991a49fa653",
    "metadata": {},
    "outputs": [],
@@ -1495,7 +1525,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 43,
    "id": "93cb2cee-9aa6-4bb8-8977-c65661d16eda",
    "metadata": {},
    "outputs": [],
@@ -1517,7 +1547,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": 44,
    "id": "a686eb61-e737-4351-8f1c-222913d47468",
    "metadata": {},
    "outputs": [
@@ -1558,7 +1588,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 45,
    "id": "e43600ba-f287-4746-8ddf-d0f71a9023ca",
    "metadata": {},
    "outputs": [
@@ -1585,7 +1615,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
+   "execution_count": 46,
    "id": "50280ead-0363-44c8-8c35-bb885d92c8b7",
    "metadata": {},
    "outputs": [
@@ -1679,7 +1709,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": 47,
    "id": "0b9e344d-03a6-4f2c-b723-67b6a20c5041",
    "metadata": {},
    "outputs": [],
@@ -1701,20 +1731,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 47,
+   "execution_count": 48,
    "id": "ad56a263-3d2e-4d91-98bf-d0b68d3c7fc3",
    "metadata": {},
    "outputs": [],
    "source": [
     "max_length = 4\n",
-    "dataloader = create_dataloader_v1(raw_text, batch_size=8, max_length=max_length, stride=max_length, shuffle=False)\n",
+    "dataloader = create_dataloader_v1(\n",
+    "    raw_text, batch_size=8, max_length=max_length,\n",
+    "    stride=max_length, shuffle=False\n",
+    ")\n",
     "data_iter = iter(dataloader)\n",
     "inputs, targets = next(data_iter)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": 49,
    "id": "84416b60-3707-4370-bcbc-da0b62f2b64d",
    "metadata": {},
    "outputs": [
@@ -1744,7 +1777,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": 50,
    "id": "7766ec38-30d0-4128-8c31-f49f063c43d1",
    "metadata": {},
    "outputs": [
@@ -1771,7 +1804,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 50,
+   "execution_count": 51,
    "id": "cc048e20-7ac8-417e-81f5-8fe6f9a4fe07",
    "metadata": {},
    "outputs": [],
@@ -1782,7 +1815,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 51,
+   "execution_count": 52,
    "id": "c369a1e7-d566-4b53-b398-d6adafb44105",
    "metadata": {},
    "outputs": [
@@ -1809,7 +1842,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 52,
+   "execution_count": 53,
    "id": "b22fab89-526e-43c8-9035-5b7018e34288",
    "metadata": {},
    "outputs": [