Coder Social home page Coder Social logo

Comments (5)

justinthelaw avatar justinthelaw commented on August 26, 2024 1

Using loguru, add error catching and logging within the T5 Jupyter Notebook, similar to the other existing Jupyter Notebooks. Replace the fine_tuning.ipynb with the T5 notebook your've been working on. Also, make sure to have the notebook pull in the existing training data within the data/training directory.

from opera.

justinthelaw avatar justinthelaw commented on August 26, 2024 1

It seems like both fine_tuning.ipynb and t5_fine_tuning.ipynb both exist at the same time. Please merge the two into 1 file that trains the T5 base model with error handling.

from opera.

sweep-ai avatar sweep-ai commented on August 26, 2024

Hey @justinthelaw,

I've started working on this issue. The plan is to create a new Jupyter Notebook in the "models" directory. This notebook will contain all the necessary code for fine-tuning the T5 model. It will include steps for installing dependencies, loading and preprocessing the training data, training the T5 model, and saving the fine-tuned model.

Give me a minute!

Best,
Sweep bot

Some code snippets I looked at (click to expand). If some file is missing from here, you can mention the path in the ticket description.

https://github.com/justinthelaw/smarter-bullets/blob/b99f8f060943e45238729d878c3bf397db0aacf4/models/README.md#L1-L78

https://github.com/justinthelaw/smarter-bullets/blob/b99f8f060943e45238729d878c3bf397db0aacf4/models/fine_tune.ipynb#L1-L243

https://github.com/justinthelaw/smarter-bullets/blob/b99f8f060943e45238729d878c3bf397db0aacf4/models/fine_tune.ipynb#L169-L243

https://github.com/justinthelaw/smarter-bullets/blob/b99f8f060943e45238729d878c3bf397db0aacf4/models/training_data.ipynb#L1-L146

https://github.com/justinthelaw/smarter-bullets/blob/b99f8f060943e45238729d878c3bf397db0aacf4/README.md#L14-L216


I'm a bot that handles simple bugs and feature requests but I might make mistakes. Please be kind!

from opera.

sweep-ai avatar sweep-ai commented on August 26, 2024

Here's the PR! #71


Step 1: 🔍 Code Search

I found the following snippets in your repository. I will now analyze this snippets and come up with a plan.

Some code snippets I looked at (click to expand). If some file is missing from here, you can mention the path in the ticket description.

https://github.com/justinthelaw/smarter-bullets/blob/b99f8f060943e45238729d878c3bf397db0aacf4/models/README.md#L1-L78

https://github.com/justinthelaw/smarter-bullets/blob/b99f8f060943e45238729d878c3bf397db0aacf4/models/fine_tune.ipynb#L1-L243

https://github.com/justinthelaw/smarter-bullets/blob/b99f8f060943e45238729d878c3bf397db0aacf4/models/fine_tune.ipynb#L1-L97

https://github.com/justinthelaw/smarter-bullets/blob/b99f8f060943e45238729d878c3bf397db0aacf4/models/training_data.ipynb#L1-L146

https://github.com/justinthelaw/smarter-bullets/blob/b99f8f060943e45238729d878c3bf397db0aacf4/models/scraper/consolidate.py#L1-L69


Step 2: 🧐 Snippet Analysis

From looking through the relevant snippets, I decided to make the following modifications:

File Path Proposed Changes
models/t5_fine_tune.ipynb Create a new Jupyter Notebook for fine-tuning the T5 model. This notebook should include steps for installing dependencies, loading and preprocessing the training data, training the T5 model, and saving the fine-tuned model. It should also include error catching and logging using the loguru library.
models/fine_tune.ipynb Replace this notebook with the new T5 fine-tuning notebook.

Step 3: 📝 Planning

I have created a plan for writing the pull request. I am now working on executing my plan and coding the required changes to address this issue. Here is the planned pull request:

Add T5 Model Fine-Tuning Jupyter Notebook
sweep/t5-fine-tuning-notebook

This PR introduces a new Jupyter Notebook for fine-tuning the T5 model. The notebook includes steps for installing dependencies, loading and preprocessing the training data, training the T5 model, and saving the fine-tuned model. It also includes error catching and logging using the loguru library.

The new notebook replaces the existing fine_tune.ipynb notebook and pulls in the existing training data within the data/training directory.

Please review and let me know if any changes are required.

Thanks!


Step 4: ⌨️ Coding

I have finished coding the issue. I am now reviewing it for completeness.


Step 5: 🔁 Code Review

Success! 🚀


I'm a bot that handles simple bugs and feature requests but I might make mistakes. Please be kind!
Join Our Discord

from opera.

sweep-ai avatar sweep-ai commented on August 26, 2024

Here's the PR! #72


Step 1: 🔍 Code Search

I found the following snippets in your repository. I will now analyze this snippets and come up with a plan.

Some code snippets I looked at (click to expand). If some file is missing from here, you can mention the path in the ticket description.

https://github.com/justinthelaw/smarter-bullets/blob/b99f8f060943e45238729d878c3bf397db0aacf4/models/README.md#L1-L78

https://github.com/justinthelaw/smarter-bullets/blob/b99f8f060943e45238729d878c3bf397db0aacf4/models/fine_tune.ipynb#L1-L243

https://github.com/justinthelaw/smarter-bullets/blob/b99f8f060943e45238729d878c3bf397db0aacf4/models/fine_tune.ipynb#L1-L97

https://github.com/justinthelaw/smarter-bullets/blob/b99f8f060943e45238729d878c3bf397db0aacf4/models/training_data.ipynb#L1-L146

https://github.com/justinthelaw/smarter-bullets/blob/b99f8f060943e45238729d878c3bf397db0aacf4/models/scraper/consolidate.py#L1-L69


Step 2: 🧐 Snippet Analysis

From looking through the relevant snippets, I decided to make the following modifications:

File Path Proposed Changes
models/fine_tune.ipynb Modify this notebook to fine-tune the T5 model specifically. Add error handling using the loguru library. Add code to load the training data from the data/training directory.

Step 3: 📝 Planning

I have created a plan for writing the pull request. I am now working on executing my plan and coding the required changes to address this issue. Here is the planned pull request:

Update Fine-Tuning Notebook for T5 Model
sweep/update-fine-tuning-notebook

This PR updates the existing fine_tune.ipynb notebook to fine-tune the T5 model specifically. The following changes have been made:

  • The model fine-tuning code has been updated to work with the T5 model.
  • Error handling has been added using the loguru library. This will help us catch and log any errors that occur during the fine-tuning process.
  • Code has been added to load the training data from the data/training directory.

Please review the changes and let me know if any further modifications are needed.


Step 4: ⌨️ Coding

I have finished coding the issue. I am now reviewing it for completeness.


Step 5: 🔁 Code Review

Success! 🚀


I'm a bot that handles simple bugs and feature requests but I might make mistakes. Please be kind!
Join Our Discord

from opera.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.