Merge branch 'dev'

README.md

@@ -106,6 +106,7 @@ Several folders contain optional materials as a bonus for interested readers:
 - **Chapter 7:**
   - [Dataset Utilities for Finding Near Duplicates and Creating Passive Voice Entries](ch07/02_dataset-utilities)
   - [Evaluating Instruction Responses Using the OpenAI API and Ollama](ch07/03_model-evaluation)
+  - [Generating a Dataset for Instruction Finetuning](ch07/05_dataset-generation)
 
 <br>
 &nbsp

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

@@ -1347,6 +1347,8 @@
    ],
    "source": [
     "import matplotlib.pyplot as plt\n",
+    "from matplotlib.ticker import MaxNLocator\n",
+    "\n",
     "\n",
     "def plot_losses(epochs_seen, tokens_seen, train_losses, val_losses):\n",
     "    fig, ax1 = plt.subplots(figsize=(5, 3))\n",
@@ -1357,6 +1359,7 @@
     "    ax1.set_xlabel(\"Epochs\")\n",
     "    ax1.set_ylabel(\"Loss\")\n",
     "    ax1.legend(loc=\"upper right\")\n",
+    "    ax1.xaxis.set_major_locator(MaxNLocator(integer=True))  # only show integer labels on x-axis\n",
     "\n",
     "    # Create a second x-axis for tokens seen\n",
     "    ax2 = ax1.twiny()  # Create a second x-axis that shares the same y-axis\n",
@@ -2455,7 +2458,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.6"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,

ch05/03_bonus_pretraining_on_gutenberg/previous_chapters.py

@@ -12,7 +12,7 @@
 import torch.nn as nn
 from torch.utils.data import Dataset, DataLoader
 import matplotlib.pyplot as plt
-
+from matplotlib.ticker import MaxNLocator
 
 #####################################
 # Chapter 2
@@ -295,6 +295,7 @@ def plot_losses(epochs_seen, tokens_seen, train_losses, val_losses, output_dir):
     ax1.set_xlabel("Epochs")
     ax1.set_ylabel("Loss")
     ax1.legend(loc="upper right")
+    ax1.xaxis.set_major_locator(MaxNLocator(integer=True))
 
     # Create a second x-axis for tokens seen
     ax2 = ax1.twiny()  # Create a second x-axis that shares the same y-axis