From 0b6665939bc18a4a8e25c6ff5ef9db6243ed8c0b Mon Sep 17 00:00:00 2001 From: rasbt Date: Thu, 9 May 2024 09:09:26 -0500 Subject: [PATCH 1/2] clarify overfitting --- ch06/01_main-chapter-code/ch06.ipynb | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/ch06/01_main-chapter-code/ch06.ipynb b/ch06/01_main-chapter-code/ch06.ipynb index aadb4ba..546fd66 100644 --- a/ch06/01_main-chapter-code/ch06.ipynb +++ b/ch06/01_main-chapter-code/ch06.ipynb @@ -2043,7 +2043,7 @@ "metadata": {}, "source": [ "- We can see that the training and test set performances are practically identical\n", - "- However, based on the slightly lower test set performance, we can see that the model overfits the training data to a very small degree\n", + "- However, based on the slightly lower test set performance, we can see that the model overfits the training data to a very small degree, as well as the validation data that has been used for tweaking some of the hyperparameters, such as the learning rate\n", "- This is normal, however, and this gap could potentially be further reduced by increasing the model's dropout rate (`drop_rate`) or the `weight_decay` in the optimizer setting" ] }, @@ -2265,7 +2265,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.10.12" + "version": "3.10.6" } }, "nbformat": 4, From b67ef1a2b2513f401782f75a341b070aabb1b382 Mon Sep 17 00:00:00 2001 From: Sebastian Raschka Date: Thu, 9 May 2024 21:15:09 -0500 Subject: [PATCH 2/2] fix punctuation and improve explanation --- setup/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/setup/README.md b/setup/README.md index 7d59cce..91d3dd6 100644 --- a/setup/README.md +++ b/setup/README.md @@ -58,7 +58,7 @@ cd LLMs-from-scratch pip install -r requirements.txt ``` -(In contrast to Google Colab, these only need to be executed once since the Lightning AI Studion environments are persistent). +(In contrast to Google Colab, these only need to be executed once since the Lightning AI Studio environments are persistent, even if you switch between CPU and GPU machines.) Then, navigate to the Python script or Jupyter Notebook you want to run. Optionally, you can also easily connect a GPU to accelerate the code's runtime, for example, when you are pretraining the LLM in chapter 5 or finetuning it in chapters 6 and 7. @@ -87,4 +87,4 @@ You can optionally run the code on a GPU by changing the *Runtime* as illustrate ## Questions? -If you have any questions, please don't hesitate to reach out via the [Discussions](https://github.com/rasbt/LLMs-from-scratch/discussions) forum in this GitHub repository. \ No newline at end of file +If you have any questions, please don't hesitate to reach out via the [Discussions](https://github.com/rasbt/LLMs-from-scratch/discussions) forum in this GitHub repository.