-
Notifications
You must be signed in to change notification settings - Fork 6.5k
feat(generativeai): Create genai_sdk_supervised_checkpoints_create_example.py #13345
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hello @yishan-pu, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!
Summary of Changes
This pull request adds a new example, genai_sdk_supervised_checkpoints_create_example.py
, demonstrating how to create a tuning job with checkpoints using the Gemini API. The example showcases how to configure a tuning job to export intermediate checkpoints and then iterates through the checkpoints to display their information.
Highlights
- New Example: Introduces
genai_sdk_supervised_checkpoints_create_example.py
to illustrate the creation of a tuning job with checkpoints. - Checkpoint Configuration: Demonstrates how to set
export_last_checkpoint_only
toFalse
to enable the export of intermediate checkpoints during tuning. - Checkpoint Iteration: Shows how to access and print information about each checkpoint within a tuning job's results.
Changelog
- generative_ai/model_tuning/genai_sdk_supervised_checkpoints_create_example.py
- Adds a new example file demonstrating how to create a tuning job with checkpoints using the Gemini API.
- Includes code to configure the tuning job to export intermediate checkpoints.
- Iterates through the checkpoints and prints their details, such as checkpoint ID, epoch, step, and endpoint.
- Uses
google.genai
andgoogle.genai.types
for interacting with the Gemini API. - Includes a placeholder for the project ID that the user needs to update.
Using Gemini Code Assist
The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.
Invoking Gemini
You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command>
or @gemini-code-assist <command>
. Below is a summary of the supported commands.
Feature | Command | Description |
---|---|---|
Code Review | /gemini review |
Performs a code review for the current pull request in its current state. |
Pull Request Summary | /gemini summary |
Provides a summary of the current pull request in its current state. |
Comment | @gemini-code-assist | Responds in comments when explicitly tagged, both in issue comments and review comments. |
Help | /gemini help |
Displays a list of available commands. |
Customization
To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/
folder in the base of the repository. Detailed instructions can be found here.
Limitations & Feedback
Gemini Code Assist is currently in preview and may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments to provide feedback.
You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.
A checkpoint's gleam,
A model's progress shown,
Insights softly bloom.
Footnotes
-
Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code Review
The code adds an example for creating a tuning job with checkpoints. The example is well-structured and easy to understand. However, there are a few minor improvements that can be made to enhance readability and maintainability.
Summary of Findings
- TODO comment: The code contains a TODO comment that should be addressed before merging. Consider providing a default value or prompting the user for input.
- Magic number: The code uses a magic number (60) for the sleep duration. Consider defining a constant with a descriptive name for better readability and maintainability.
Merge Readiness
The code is generally ready to be merged, but the TODO comment and magic number should be addressed first. I am unable to approve the pull request, and users should have others review and approve this code before merging.
# TODO(developer): Update and un-comment below lines | ||
# PROJECT_ID = "your-project-id" |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
while tuning_job.state in running_states: | ||
print(tuning_job.state) | ||
tuning_job = client.tunings.get(name=tuning_job.name) | ||
time.sleep(60) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Here is the summary of possible violations 😱 There is a possible violation for not having product prefix.
The end of the violation section. All the stuff below is FYI purposes only. Here is the summary of changes. You are about to add 1 region tag.
This comment is generated by snippet-bot.
|
Add an example for creating a tuning job with checkpoints.