Readability and code quality improvements (#959)

* Consistent dataset naming

* consistent section headers

ch05/01_main-chapter-code/exercise-solutions.ipynb

@@ -62,7 +62,8 @@
    "id": "5fea8be3-30a1-4623-a6d7-b095c6c1092e",
    "metadata": {},
    "source": [
-    "# Exercise 5.1: Temperature-scaled softmax scores and sampling probabilities"
+    " \n",
+    "## Exercise 5.1: Temperature-scaled softmax scores and sampling probabilities"
    ]
   },
   {
@@ -239,7 +240,8 @@
    "id": "b510ffb0-adca-4d64-8a12-38c4646fd736",
    "metadata": {},
    "source": [
-    "# Exercise 5.2: Different temperature and top-k settings"
+    " \n",
+    "## Exercise 5.2: Different temperature and top-k settings"
    ]
   },
   {
@@ -258,7 +260,8 @@
    "id": "3f35425d-529d-4179-a1c4-63cb8b25b156",
    "metadata": {},
    "source": [
-    "# Exercise 5.3: Deterministic behavior in the decoding functions"
+    " \n",
+    "## Exercise 5.3: Deterministic behavior in the decoding functions"
    ]
   },
   {
@@ -425,7 +428,8 @@
    "id": "6d0480e5-fb4e-41f8-a161-7ac980d71d47",
    "metadata": {},
    "source": [
-    "# Exercise 5.4: Continued pretraining"
+    " \n",
+    "## Exercise 5.4: Continued pretraining"
    ]
   },
   {
@@ -598,7 +602,8 @@
    "id": "3384e788-f5a1-407c-8dd1-87959b75026d",
    "metadata": {},
    "source": [
-    "# Exercise 5.5: Training and validation set losses of the pretrained model"
+    " \n",
+    "## Exercise 5.5: Training and validation set losses of the pretrained model"
    ]
   },
   {
@@ -874,7 +879,8 @@
    "id": "3a76a1e0-9635-480a-9391-3bda7aea402d",
    "metadata": {},
    "source": [
-    "# Exercise 5.6: Trying larger models"
+    " \n",
+    "## Exercise 5.6: Trying larger models"
    ]
   },
   {
@@ -1028,7 +1034,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.16"
+   "version": "3.13.5"
   }
  },
  "nbformat": 4,