Fix 3 documentation issues in basic_training_loops guide

[Jah-yee]

Good day,

I noticed three issues while reviewing the basic_training_loops guide and would like to propose the following fixes:

Fix 1: Incorrect color description in visualization text

In the markdown cell before the first plotting example, the text incorrectly states that predictions are shown "in red" and training data "in blue", but the actual code uses default matplotlib colors with no explicit color specification.

Before: "Before training the model, you can visualize the loss value by plotting the model's predictions in red and the training data in blue:"

After: "Before training the model, you can visualize the loss value by plotting the model's predictions and the training data:"

Fix 2: Improved gradient variable naming for clarity

In the train function, the gradient variables were named dw and db, which could be confused with the weight and bias variables (model.w, model.b). Renamed to grad_w and grad_b to clearly indicate they are gradients, matching the standard gradient descent notation.

Fix 3: Keras save_weights filename bug

The code keras_model.save_weights("my_checkpoint") produces a ValueError because Keras save_weights requires the explicit .weights.h5 extension. Changed to keras_model.save_weights("my_checkpoint.weights.h5").

These issues were reported by a reader in tensorflow/tensorflow#116299.

Thank you for your attention. If there are any issues or suggestions, please leave a comment and I will address them promptly.

Warmly,
RoomWithOutRoof

[google-cla]

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

[github-actions]

Preview

Preview and run these notebook edits with Google Colab:

• site/en/guide/basic_training_loops.ipynb

Rendered notebook diffs available on ReviewNB.com.

Format and style

Use the TensorFlow docs notebook tools to format for consistent source diffs and lint for style:

$ python3 -m pip install -U --user git+https://github.com/tensorflow/docs

$ python3 -m tensorflow_docs.tools.nbfmt notebook.ipynb

$ python3 -m tensorflow_docs.tools.nblint --arg=repo:tensorflow/docs notebook.ipynb

If commits are added to the pull request, synchronize your local branch: git pull origin fix-tensorflow-docs-issues