Training in progress, step 20

.bandit

@@ -0,0 +1,3 @@
+[bandit]
+exclude = tests
+skips = B101

.editorconfig

@@ -0,0 +1,14 @@
+root = true
+
+[*]
+end_of_line = lf
+insert_final_newline = true
+trim_trailing_whitespace = true
+
+[*.py]
+indent_style = space
+indent_size = 4
+
+[**.yml]
+indent_style = space
+indent_size = 2

.flake8

@@ -0,0 +1,5 @@
+[flake8]
+max-line-length = 88
+
+select = C,E,F,W,B,B950
+extend-ignore = E203, E501, W503

.gitattributes

@@ -1,43 +1,9 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+data/*.jsonl filter=lfs diff=lfs merge=lfs -text
+adapter_model.safetensors filter=lfs diff=lfs merge=lfs -text
+docs/images/4d-mask.png filter=lfs diff=lfs merge=lfs -text
+docs/images/ray-cluster-dashboard.png filter=lfs diff=lfs merge=lfs -text
+image/axolotl.png filter=lfs diff=lfs merge=lfs -text
+image/sticker_fixed.png filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
-blobs/09d433f650646834a83c580877bd60c6d1f88f7755305c12576b5c7058f9af15 filter=lfs diff=lfs merge=lfs -text
-blobs/2b1879f356aed350030bb40eb45ad362c89d9891096f79a3ab323d3ba5607668 filter=lfs diff=lfs merge=lfs -text
-blobs/92ecfe1a2414458b4821ac8c13cf8cb70aed66b5eea8dc5ad9eeb4ff309d6d7b filter=lfs diff=lfs merge=lfs -text
-blobs/ab33d910f405204e5d388bc3521503584800461dc96808e287821dd451c1edac filter=lfs diff=lfs merge=lfs -text
-blobs/fc1cdddd6bfa91128d6e94ee73d0ce62bfcdb7af29e978ddcab30c66ae9ea7fa filter=lfs diff=lfs merge=lfs -text
-10gb_file filter=lfs diff=lfs merge=lfs -text
-3gb_file.dat filter=lfs diff=lfs merge=lfs -text
+tokenizer.model filter=lfs diff=lfs merge=lfs -text
+training_args.bin filter=lfs diff=lfs merge=lfs -text

.github/CODE_OF_CONDUCT.md

@@ -0,0 +1,129 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, religion, or sexual identity
+and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the
+  overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement on Discord
+at https://discord.gg/QYF8QrtEUm
+
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series
+of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or
+permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior,  harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within
+the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.0, available at
+https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct
+enforcement ladder](https://github.com/mozilla/diversity).
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see the FAQ at
+https://www.contributor-covenant.org/faq. Translations are available at
+https://www.contributor-covenant.org/translations.

.github/CONTRIBUTING.md

@@ -0,0 +1,76 @@
+# Contributing to axolotl
+
+First of all, thank you for your interest in contributing to axolotl! We appreciate the time and effort you're willing to invest in making our project better. This document provides guidelines and information to make the contribution process as smooth as possible.
+
+## Table of Contents
+
+- [Code of Conduct](#code-of-conduct)
+- [Getting Started](#getting-started)
+- [How to Contribute](#how-to-contribute)
+  - [Reporting Bugs](#reporting-bugs)
+  - [Suggesting Enhancements](#suggesting-enhancements)
+  - [Submitting Pull Requests](#submitting-pull-requests)
+- [Style Guidelines](#style-guidelines)
+  - [Code Style](#code-style)
+  - [Commit Messages](#commit-messages)
+- [Additional Resources](#additional-resources)
+
+## Code of Conduct
+
+All contributors are expected to adhere to our [Code of Conduct](CODE_OF_CONDUCT.md). Please read it before participating in the axolotl community.
+
+## Getting Started
+
+Bugs? Please check for open issue else create a new [Issue](https://github.com/axolotl-ai-cloud/axolotl/issues/new).
+
+PRs are **greatly welcome**!
+
+1. Fork the repository and clone it to your local machine.
+2. Set up the development environment by following the instructions in the [README.md](https://github.com/axolotl-ai-cloud/axolotl/tree/main/README.md) file.
+3. Explore the codebase, run tests, and verify that everything works as expected.
+
+Please run below to setup env
+```bash
+pip3 install -r requirements-dev.txt -r requirements-tests.txt
+pre-commit install
+
+# test
+pytest tests/
+```
+
+## How to Contribute
+
+### Reporting Bugs
+
+If you encounter a bug or issue while using axolotl, please open a new issue on the [GitHub Issues](https://github.com/axolotl-ai-cloud/axolotl/issues) page. Provide a clear and concise description of the problem, steps to reproduce it, and any relevant error messages or logs.
+
+### Suggesting Enhancements
+
+We welcome ideas for improvements and new features. To suggest an enhancement, open a new issue on the [GitHub Issues](https://github.com/axolotl-ai-cloud/axolotl/issues) page. Describe the enhancement in detail, explain the use case, and outline the benefits it would bring to the project.
+
+### Submitting Pull Requests
+
+1. Create a new branch for your feature or bugfix. Use a descriptive name like `feature/your-feature-name` or `fix/your-bugfix-name`.
+2. Make your changes, following the [Style Guidelines](#style-guidelines) below.
+3. Test your changes and ensure that they don't introduce new issues or break existing functionality.
+4. Commit your changes, following the [commit message guidelines](#commit-messages).
+5. Push your branch to your fork on GitHub.
+6. Open a new pull request against the `main` branch of the axolotl repository. Include a clear and concise description of your changes, referencing any related issues.
+
+## Style Guidelines
+
+### Code Style
+
+axolotl uses [{codestyle}]({URLofCodestyle}) as its code style guide. Please ensure that your code follows these guidelines.
+
+### Commit Messages
+
+Write clear and concise commit messages that briefly describe the changes made in each commit. Use the imperative mood and start with a capitalized verb, e.g., "Add new feature" or "Fix bug in function".
+
+## Additional Resources
+
+- [GitHub Help](https://help.github.com/)
+- [GitHub Pull Request Documentation](https://docs.github.com/en/github/collaborating-with-issues-and-pull-requests)
+- [{codestyle}]({URLofCodestyle})
+
+Thank you once again for your interest in contributing to axolotl. We look forward to collaborating with you and creating an even better project together!

.github/FUNDING.yml

@@ -0,0 +1,13 @@
+# These are supported funding model platforms
+
+github: [winglian, OpenAccess-AI-Collective] # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2]
+patreon: # Replace with a single Patreon username
+open_collective: # Replace with a single Open Collective username
+ko_fi: axolotl_ai # Replace with a single Ko-fi username
+tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
+community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
+liberapay: # Replace with a single Liberapay username
+issuehunt: # Replace with a single IssueHunt username
+otechie: # Replace with a single Otechie username
+lfx_crowdfunding: # Replace with a single LFX Crowdfunding project-name e.g., cloud-foundry
+custom: ['https://quickchart.io/qr?text=bitcoin%3Abc1qxlgwlqwfea5s2cxm42xqsfmwjct0rj8w8ea5np&size=480&centerImageUrl=https%3A%2F%2Fupload.wikimedia.org%2Fwikipedia%2Fcommons%2Fthumb%2F4%2F46%2FBitcoin.svg%2F64px-Bitcoin.svg.png'] # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']

.github/ISSUE_TEMPLATE/bug-report.yaml

@@ -0,0 +1,113 @@
+name: Bug Report
+description: File a bug report
+labels: ["bug", "needs triage"]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        ## Before you start
+        Please **make sure you are on the latest version.**
+        If you encountered the issue after you installed, updated, or reloaded, **please try restarting before reporting the bug**.
+
+  - type: checkboxes
+    id: no-duplicate-issues
+    attributes:
+      label: "Please check that this issue hasn't been reported before."
+      description: "The **Label filters** may help make your search more focussed."
+      options:
+        - label: "I searched previous [Bug Reports](https://github.com/axolotl-ai-cloud/axolotl/labels/bug) didn't find any similar reports."
+          required: true
+
+  - type: textarea
+    id: expected
+    attributes:
+      label: Expected Behavior
+      description: Tell us what **should** happen.
+    validations:
+      required: true
+
+  - type: textarea
+    id: what-happened
+    attributes:
+      label: Current behaviour
+      description: |
+        Tell us what happens instead of the expected behavior.
+        Provide stacktrace and/or screenshots.
+    validations:
+      required: true
+
+  - type: textarea
+    id: reproduce
+    attributes:
+      label: Steps to reproduce
+      description: |
+        Which exact steps can a developer take to reproduce the issue?
+        The more detail you provide, the easier it will be to narrow down and fix the bug.
+        Please paste in tasks and/or queries **as text, not screenshots**.
+      placeholder: |
+        Example of the level of detail needed to reproduce any bugs efficiently and reliably.
+        1. Go to the '...' page.
+        2. Click on the '...' button.
+        3. Scroll down to '...'.
+        4. Observe the error.
+    validations:
+      required: true
+
+  - type: textarea
+    id: config
+    attributes:
+      label: Config yaml
+      description: |
+        Please attach the config yaml!
+      render: yaml
+
+  - type: textarea
+    id: possible-solution
+    attributes:
+      label: Possible solution
+      description: |
+        Not obligatory, but please suggest a fix or reason for the bug, if you have an idea.
+
+
+  - type: checkboxes
+    id: operating-systems
+    attributes:
+      label: Which Operating Systems are you using?
+      description: You may select more than one.
+      options:
+        - label: Linux
+        - label: macOS
+        - label: Windows
+
+  - type: input
+    id: Python-version
+    attributes:
+      label: Python Version
+      description: Which {Programming} version are you using?
+      placeholder: 3.10 / please change accordingly
+    validations:
+      required: true
+
+  - type: input
+    id: axolotl-branch-commit
+    attributes:
+      label: axolotl branch-commit
+      description: On which branch/commit are you?
+      placeholder: main/4d6490b
+    validations:
+      required: true
+
+  - type: checkboxes
+    id: acknowledgements
+    attributes:
+      label: 'Acknowledgements'
+      description: 'Please confirm the following:'
+      options:
+        - label: 'My issue title is concise, descriptive, and in title casing.'
+          required: true
+        - label: 'I have searched the existing issues to make sure this bug has not been reported yet.'
+          required: true
+        - label: 'I am using the latest version of axolotl.'
+          required: true
+        - label: 'I have provided enough information for the maintainers to reproduce and diagnose the issue.'
+          required: true

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,7 @@
+blank_issues_enabled: false
+contact_links:
+  - name: Ask a question
+    url: https://github.com/axolotl-ai-cloud/axolotl/discussions/categories/q-a
+    about: Ask questions and discuss with other community members
+  - name: Discuss the Project in Discord
+    url: https://discord.gg/HhrNrHJPRb

.github/ISSUE_TEMPLATE/docs.yml

@@ -0,0 +1,46 @@
+name: Documentation Improvement / Clarity
+description: Make a suggestion to improve the project documentation.
+labels: ['needs triage', 'docs']
+body:
+  - type: markdown
+    attributes:
+      value: '## :book: Documentation :book:'
+  - type: markdown
+    attributes:
+      value: |
+        * Ask questions in [Discord](https://discord.gg/HhrNrHJPRb).
+        * Before you file an issue read the [Contributing guide](./CONTRIBUTING.md).
+        * Check to make sure someone hasn't already opened a [similar issue](https://github.com/axolotl-ai-cloud/axolotl/issues).
+  - type: textarea
+    attributes:
+      label: What piece of documentation is affected?
+      description: Please link to the article you'd like to see updated.
+    validations:
+      required: true
+  - type: textarea
+    attributes:
+      label: What part(s) of the article would you like to see updated?
+      description: |
+        - Give as much detail as you can to help us understand the change you want to see.
+        - Why should the docs be changed? What use cases does it support?
+        - What is the expected outcome?
+    validations:
+      required: true
+  - type: textarea
+    attributes:
+      label: Additional Information
+      description: Add any other context or screenshots about the feature request here.
+    validations:
+      required: false
+  - type: checkboxes
+    id: acknowledgements
+    attributes:
+      label: 'Acknowledgements'
+      description: 'Please confirm the following:'
+      options:
+        - label: 'My issue title is concise, descriptive, and in title casing.'
+          required: true
+        - label: 'I have searched the existing issues to make sure this feature has not been requested yet.'
+          required: true
+        - label: 'I have provided enough information for the maintainers to understand and evaluate this request.'
+          required: true

.github/ISSUE_TEMPLATE/feature-request.yaml

@@ -0,0 +1,63 @@
+name: Feature Request / Enhancement
+description: Suggest a new feature or feature enhancement for the project
+labels: ["enhancement", "needs triage"]
+body:
+  - type: checkboxes
+    id: no-duplicate-issues
+    attributes:
+      label: "⚠️ Please check that this feature request hasn't been suggested before."
+      description: "There are two locations for previous feature requests. Please search in both. Thank you. The **Label filters** may help make your search more focussed."
+      options:
+        - label: "I searched previous [Ideas in Discussions](https://github.com/axolotl-ai-cloud/axolotl/discussions/categories/ideas) didn't find any similar feature requests."
+          required: true
+        - label: "I searched previous [Issues](https://github.com/axolotl-ai-cloud/axolotl/labels/enhancement) didn't find any similar feature requests."
+          required: true
+
+  - type: textarea
+    id: feature-description
+    validations:
+      required: true
+    attributes:
+      label: "🔖 Feature description"
+      description: "A clear and concise description of what the feature request is."
+      placeholder: "You should add ..."
+
+  - type: textarea
+    id: solution
+    validations:
+      required: true
+    attributes:
+      label: "✔️ Solution"
+      description: "A clear and concise description of what you want to happen, and why."
+      placeholder: "In my use-case, ..."
+
+  - type: textarea
+    id: alternatives
+    validations:
+      required: false
+    attributes:
+      label: "❓ Alternatives"
+      description: "A clear and concise description of any alternative solutions or features you've considered."
+      placeholder: "I have considered ..."
+
+  - type: textarea
+    id: additional-context
+    validations:
+      required: false
+    attributes:
+      label: "📝 Additional Context"
+      description: "Add any other context or screenshots about the feature request here."
+      placeholder: "..."
+
+  - type: checkboxes
+    id: acknowledgements
+    attributes:
+      label: 'Acknowledgements'
+      description: 'Please confirm the following:'
+      options:
+        - label: 'My issue title is concise, descriptive, and in title casing.'
+          required: true
+        - label: 'I have searched the existing issues to make sure this feature has not been requested yet.'
+          required: true
+        - label: 'I have provided enough information for the maintainers to understand and evaluate this request.'
+          required: true

.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,27 @@
+<!--- Provide a general summary of your changes in the Title above -->
+
+# Description
+
+<!--- Describe your changes in detail -->
+
+## Motivation and Context
+
+<!--- Why is this change required? What problem does it solve? -->
+<!--- If it fixes an open issue, please link to the issue here. -->
+
+## How has this been tested?
+
+<!--- Please describe in detail how you tested your changes. -->
+<!--- Include details of your testing environment, tests ran to see how -->
+<!--- your change affects other areas of the code, etc. -->
+
+## Screenshots (if appropriate)
+
+## Types of changes
+
+<!--- What types of changes does your code introduce? Put an `x` in all the boxes that apply: -->
+
+## Social Handles (Optional)
+
+<!-- Thanks for submitting a bugfix or enhancement. -->
+<!-- We'd love to show our thanks to you on Twitter & Discord if you provide your handle -->

.github/SECURITY.md

@@ -0,0 +1,9 @@
+# Security Policy
+
+## Supported Versions
+
+Due to the nature of the fast development that is happening in this project, only the latest released version can be supported.
+
+## Reporting a Vulnerability
+
+If you find a vulnerability, please contact us on  [Discord](https://discord.gg/xcu3ECkH9a) rather than creating a GitHub issue to allow us some time to fix it before it is a known vulnerability to others.

.github/SUPPORT.md

@@ -0,0 +1,10 @@
+# Support
+
+If you need help with this project or have questions, please:
+
+1. Check the documentation.
+2. Search the existing issues and pull requests.
+3. Create a new issue if your question is not answered or your problem is not solved.
+4. Have a look in the [Discord server](https://discord.gg/HhrNrHJPRb)
+
+Please note that this project is maintained by volunteers who have limited availability. We'll do our best to address your questions and concerns in a timely manner.

.github/release-drafter.yml

@@ -0,0 +1,31 @@
+name-template: 'v$RESOLVED_VERSION'
+tag-template: 'v$RESOLVED_VERSION'
+categories:
+  - title: '🚀 Features'
+    labels:
+      - 'feature'
+      - 'enhancement'
+  - title: '🐛 Bug Fixes'
+    labels:
+      - 'fix'
+      - 'bugfix'
+      - 'bug'
+  - title: '🧰 Maintenance'
+    label: 'chore'
+change-template: '- $TITLE @$AUTHOR (#$NUMBER)'
+change-title-escapes: '\<*_&' # You can add # and @ to disable mentions, and add ` to disable code blocks.
+version-resolver:
+  major:
+    labels:
+      - 'major'
+  minor:
+    labels:
+      - 'minor'
+  patch:
+    labels:
+      - 'patch'
+  default: patch
+template: |
+  ## What’s Changed
+
+  $CHANGES

.github/workflows/base.yml

@@ -0,0 +1,80 @@
+name: ci-cd-base
+
+on:
+  push:
+    branches:
+      - "main"
+    paths:
+      - 'Dockerfile-base'
+      - '.github/workflows/base.yml'
+  pull_request:
+    paths:
+      - 'Dockerfile-base'
+      - '.github/workflows/base.yml'
+  workflow_dispatch:
+
+jobs:
+  build-base:
+    if: github.repository_owner == 'axolotl-ai-cloud'
+    # this job needs to be run on self-hosted GPU runners...
+    runs-on: axolotl-gpu-runner
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - cuda: "124"
+            cuda_version: 12.4.1
+            cudnn_version: ""
+            python_version: "3.11"
+            pytorch: 2.4.1
+            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
+          - cuda: "124"
+            cuda_version: 12.4.1
+            cudnn_version: ""
+            python_version: "3.11"
+            pytorch: 2.5.1
+            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
+          - cuda: "124"
+            cuda_version: 12.4.1
+            cudnn_version: ""
+            python_version: "3.11"
+            pytorch: 2.6.0
+            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
+          - cuda: "128"
+            cuda_version: 12.8.1
+            cudnn_version: ""
+            python_version: "3.11"
+            pytorch: nightly
+            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Docker metadata
+        id: metadata
+        uses: docker/metadata-action@v5
+        with:
+          images: |
+            winglian/axolotl-base
+            axolotlai/axolotl-base
+      - name: Login to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+      - name: Build
+        uses: docker/build-push-action@v4
+        with:
+          context: .
+          file: ${{ matrix.pytorch == 'nightly' && './docker/Dockerfile-base-nightly' || './docker/Dockerfile-base' }}
+          push: ${{ github.event_name != 'pull_request' }}
+          tags: ${{ steps.metadata.outputs.tags }}-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
+          labels: ${{ steps.metadata.outputs.labels }}
+          build-args: |
+            CUDA_VERSION=${{ matrix.cuda_version }}
+            CUDNN_VERSION=${{ matrix.cudnn_version }}
+            CUDA=${{ matrix.cuda }}
+            PYTHON_VERSION=${{ matrix.python_version }}
+            PYTORCH_VERSION=${{ matrix.pytorch }}
+            TORCH_CUDA_ARCH_LIST=${{ matrix.torch_cuda_arch_list }}

.github/workflows/docs.yml

@@ -0,0 +1,34 @@
+name: Publish Docs
+on:
+  push:
+    branches:
+      - main
+
+permissions:
+    contents: write
+    pages: write
+
+jobs:
+    build-deploy:
+        runs-on: ubuntu-latest
+        steps:
+        - name: Check out repository
+          uses: actions/checkout@v4
+        - name: Set up Quarto
+          uses: quarto-dev/quarto-actions/setup@v2
+        - name: Setup Python
+          uses: actions/setup-python@v5
+          with:
+            python-version: '3.11'
+        - name: Install dependencies
+          run: |
+            python3 -m pip install jupyter quartodoc
+            python3 -m pip install -e . --no-deps
+        - name: Build autodoc
+          run: quartodoc build
+        - name: Publish to GitHub Pages (and render)
+          uses: quarto-dev/quarto-actions/publish@v2
+          with:
+            target: gh-pages
+          env:
+            GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/lint.yml

@@ -0,0 +1,24 @@
+name: lint
+on:
+  # check on PRs, and manual triggers
+  merge_group:
+  pull_request:
+      paths:
+       - '**.py'
+       - 'requirements.txt'
+       - '.github/workflows/*.yml'
+       - "*.[q]md"
+       - "examples/**/*.y[a]?ml"
+  workflow_dispatch:
+
+jobs:
+  pre-commit:
+    name: pre-commit
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+          cache: 'pip' # caching pip dependencies
+      - uses: pre-commit/action@v3.0.1

.github/workflows/main.yml

@@ -0,0 +1,176 @@
+name: ci-cd
+
+on:
+  push:
+    branches:
+      - "main"
+    tags:
+      - "v*"
+  workflow_dispatch:
+
+jobs:
+  build-axolotl:
+    if: ${{ ! contains(github.event.commits[0].message, '[skip docker]') && github.repository_owner == 'axolotl-ai-cloud' }}
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - cuda: 124
+            cuda_version: 12.4.1
+            python_version: "3.11"
+            pytorch: 2.4.1
+            axolotl_extras:
+          - cuda: 124
+            cuda_version: 12.4.1
+            python_version: "3.11"
+            pytorch: 2.5.1
+            axolotl_extras: vllm
+            is_latest: true
+          - cuda: 124
+            cuda_version: 12.4.1
+            python_version: "3.11"
+            pytorch: 2.6.0
+            axolotl_extras:
+    runs-on: axolotl-gpu-runner
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Docker metadata
+        id: metadata
+        uses: docker/metadata-action@v5
+        with:
+          images: |
+            winglian/axolotl
+            axolotlai/axolotl
+          tags: |
+            type=ref,event=branch
+            type=pep440,pattern={{version}}
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+      # guidance for testing before pushing: https://docs.docker.com/build/ci/github-actions/test-before-push/
+      - name: Build and export to Docker
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          build-args: |
+            BASE_TAG=${{ github.ref_type == 'tag' && 'main' || github.ref_name }}-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}
+            CUDA=${{ matrix.cuda }}
+            PYTORCH_VERSION=${{ matrix.pytorch }}
+            AXOLOTL_ARGS=${{ matrix.axolotl_args }}
+          file: ./docker/Dockerfile
+          push: ${{ github.event_name != 'pull_request' }}
+          tags: |
+            ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
+            ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}
+            ${{ (matrix.is_latest) && format('{0}-latest', steps.metadata.outputs.tags) || '' }}
+          labels: ${{ steps.metadata.outputs.labels }}
+
+  build-axolotl-cloud:
+    needs: build-axolotl
+    if: ${{ ! contains(github.event.commits[0].message, '[skip docker]') && github.repository_owner == 'axolotl-ai-cloud' }}
+    # this job needs to be run on self-hosted GPU runners...
+    strategy:
+      matrix:
+        include:
+          - cuda: 124
+            cuda_version: 12.4.1
+            python_version: "3.11"
+            pytorch: 2.4.1
+            axolotl_extras:
+          - cuda: 124
+            cuda_version: 12.4.1
+            python_version: "3.11"
+            pytorch: 2.5.1
+            axolotl_extras:
+            is_latest: true
+          - cuda: 124
+            cuda_version: 12.4.1
+            python_version: "3.11"
+            pytorch: 2.6.0
+            axolotl_extras:
+    runs-on: axolotl-gpu-runner
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Docker metadata
+        id: metadata
+        uses: docker/metadata-action@v5
+        with:
+          images: |
+            winglian/axolotl-cloud
+            axolotlai/axolotl-cloud
+          tags: |
+            type=ref,event=branch
+            type=pep440,pattern={{version}}
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+      - name: Build
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          build-args: |
+            BASE_TAG=${{ github.ref_type == 'tag' && 'main' || github.ref_name }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
+            CUDA=${{ matrix.cuda }}
+          file: ./docker/Dockerfile-cloud
+          push: ${{ github.event_name != 'pull_request' }}
+          tags: |
+             ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
+             ${{ (matrix.is_latest) && format('{0}-latest', steps.metadata.outputs.tags) || '' }}
+          labels: ${{ steps.metadata.outputs.labels }}
+
+  build-axolotl-cloud-no-tmux:
+    needs: build-axolotl
+    if: ${{ ! contains(github.event.commits[0].message, '[skip docker]') && github.repository_owner == 'axolotl-ai-cloud' }}
+    # this job needs to be run on self-hosted GPU runners...
+    strategy:
+      matrix:
+        include:
+          - cuda: 124
+            cuda_version: 12.4.1
+            python_version: "3.11"
+            pytorch: 2.4.1
+            axolotl_extras:
+    runs-on: axolotl-gpu-runner
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Docker metadata
+        id: metadata
+        uses: docker/metadata-action@v5
+        with:
+          images: |
+            winglian/axolotl-cloud-term
+            axolotlai/axolotl-cloud-term
+          tags: |
+            type=ref,event=branch
+            type=pep440,pattern={{version}}
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+      - name: Build
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          build-args: |
+            BASE_TAG=${{ github.ref_type == 'tag' && 'main' || github.ref_name }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
+            CUDA=${{ matrix.cuda }}
+          file: ./docker/Dockerfile-cloud-no-tmux
+          push: ${{ github.event_name != 'pull_request' }}
+          tags: |
+             ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
+             ${{ (matrix.is_latest) && format('{0}-latest', steps.metadata.outputs.tags) || '' }}
+          labels: ${{ steps.metadata.outputs.labels }}

.github/workflows/multi-gpu-e2e.yml

@@ -0,0 +1,73 @@
+name: docker-multigpu-tests-biweekly
+
+on:
+  pull_request:
+    paths:
+      - 'tests/e2e/multigpu/*.py'
+      - 'requirements.txt'
+      - 'setup.py'
+      - 'pyproject.toml'
+      - '.github/workflows/multi-gpu-e2e.yml'
+  workflow_dispatch:
+  schedule:
+    - cron: '0 0 * * 1,4'  # Runs at 00:00 UTC every monday & thursday
+
+# Cancel jobs on the same ref if a new one is triggered
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+
+jobs:
+  test-axolotl-multigpu:
+    if: ${{ ! contains(github.event.commits[0].message, '[skip e2e]') && github.repository_owner == 'axolotl-ai-cloud' }}
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - cuda: 124
+            cuda_version: 12.4.1
+            python_version: "3.11"
+            pytorch: 2.4.1
+            axolotl_extras:  # no vllm support for 2.4.1
+            num_gpus: 2
+            nightly_build: "true"
+          - cuda: 124
+            cuda_version: 12.4.1
+            python_version: "3.11"
+            pytorch: 2.5.1
+            axolotl_extras: vllm
+            num_gpus: 2
+            nightly_build: "true"
+          - cuda: 124
+            cuda_version: 12.4.1
+            python_version: "3.11"
+            pytorch: 2.6.0
+            # awaiting vllm#12721
+            axolotl_extras:
+            num_gpus: 2
+            nightly_build: "true"
+    runs-on: [self-hosted, modal]
+    timeout-minutes: 120
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Install Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+      - name: Install Modal
+        run: |
+          python -m pip install --upgrade pip
+          pip install modal==0.71.8 jinja2
+      - name: Update env vars
+        run: |
+          echo "BASE_TAG=main-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV
+          echo "PYTORCH_VERSION=${{ matrix.pytorch}}" >> $GITHUB_ENV
+          echo "AXOLOTL_ARGS=${{ matrix.axolotl_args}}" >> $GITHUB_ENV
+          echo "AXOLOTL_EXTRAS=${{ matrix.axolotl_extras}}" >> $GITHUB_ENV
+          echo "CUDA=${{ matrix.cuda }}" >> $GITHUB_ENV
+          echo "N_GPUS=${{ matrix.num_gpus }}" >> $GITHUB_ENV
+          echo "NIGHTLY_BUILD=${{ matrix.nightly_build }}" >> $GITHUB_ENV
+      - name: Run tests job on Modal
+        run: |
+          modal run cicd.multigpu

.github/workflows/nightlies.yml

@@ -0,0 +1,119 @@
+name: docker-nightlies
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: '0 0 * * *'  # Runs at 00:00 UTC every day
+
+jobs:
+  build-axolotl:
+    if: ${{ ! contains(github.event.commits[0].message, '[skip docker]') && github.repository_owner == 'axolotl-ai-cloud' }}
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - cuda: 124
+            cuda_version: 12.4.1
+            python_version: "3.11"
+            pytorch: 2.4.1
+            axolotl_extras:
+          - cuda: 124
+            cuda_version: 12.4.1
+            python_version: "3.11"
+            pytorch: 2.5.1
+            axolotl_extras:
+          - cuda: 124
+            cuda_version: 12.4.1
+            python_version: "3.11"
+            pytorch: 2.6.0
+            axolotl_extras:
+    runs-on: axolotl-gpu-runner
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Docker metadata
+        id: metadata
+        uses: docker/metadata-action@v5
+        with:
+          images: |
+            winglian/axolotl
+            axolotlai/axolotl
+          tags: |
+            type=raw,value={{ branch }}-{{ date 'YYYYMMDD' }}
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+      # guidance for testing before pushing: https://docs.docker.com/build/ci/github-actions/test-before-push/
+      - name: Build and export to Docker
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          build-args: |
+            BASE_TAG=${{ github.ref_name }}-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}
+            CUDA=${{ matrix.cuda }}
+            PYTORCH_VERSION=${{ matrix.pytorch }}
+            AXOLOTL_ARGS=${{ matrix.axolotl_args }}
+          file: ./docker/Dockerfile
+          push: ${{ github.event_name != 'pull_request' }}
+          tags: |
+            ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
+          labels: ${{ steps.metadata.outputs.labels }}
+
+  build-axolotl-cloud:
+    needs: build-axolotl
+    if: ${{ ! contains(github.event.commits[0].message, '[skip docker]') && github.repository_owner == 'axolotl-ai-cloud' }}
+    # this job needs to be run on self-hosted GPU runners...
+    strategy:
+      matrix:
+        include:
+          - cuda: 124
+            cuda_version: 12.4.1
+            python_version: "3.11"
+            pytorch: 2.4.1
+            axolotl_extras:
+          - cuda: 124
+            cuda_version: 12.4.1
+            python_version: "3.11"
+            pytorch: 2.5.1
+            axolotl_extras:
+          - cuda: 124
+            cuda_version: 12.4.1
+            python_version: "3.11"
+            pytorch: 2.6.0
+            axolotl_extras:
+    runs-on: axolotl-gpu-runner
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Docker metadata
+        id: metadata
+        uses: docker/metadata-action@v5
+        with:
+          images: |
+            winglian/axolotl-cloud
+            axolotlai/axolotl-cloud
+          tags: |
+            type=raw,value={{ branch }}-{{ date 'YYYYMMDD' }}
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+      - name: Build
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          build-args: |
+            BASE_TAG=${{ github.ref_name }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
+            CUDA=${{ matrix.cuda }}
+          file: ./docker/Dockerfile-cloud
+          push: ${{ github.event_name != 'pull_request' }}
+          tags: |
+             ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
+          labels: ${{ steps.metadata.outputs.labels }}

.github/workflows/precommit-autoupdate.yml

@@ -0,0 +1,49 @@
+name: Pre-commit auto-update
+
+on:
+  schedule:
+    - cron: '0 0 * * 0'  # Run weekly
+  workflow_dispatch:  # Manual kickoff
+
+jobs:
+  auto-update:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+      pull-requests: write
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
+      - name: Update pre-commit hooks
+        id: update
+        run: |
+          pip install pre-commit
+          pre-commit autoupdate
+          if [[ -n $(git status --porcelain) ]]; then
+            echo "changes=true" >> $GITHUB_OUTPUT
+            git diff .pre-commit-config.yaml > pre-commit-update.diff
+          fi
+
+      - name: Create Pull Request
+        if: steps.update.outputs.changes == 'true'
+        uses: peter-evans/create-pull-request@v6
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          branch: update/pre-commit-hooks
+          delete-branch: true
+          title: "chore: update pre-commit hooks"
+          commit-message: "chore: update pre-commit hooks"
+          body: |
+            Automated PR to update pre-commit hooks to their latest versions.
+
+            <details>
+            <summary>Changes:</summary>
+
+            ```diff
+            ${{ steps.update.outputs.diff }}
+            ```
+            </details>

.github/workflows/pypi.yml

@@ -0,0 +1,60 @@
+name: publish pypi
+
+on:
+  push:
+    tags:
+      - 'v*'
+  workflow_dispatch:
+
+jobs:
+  setup_release:
+    name: Create Release
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Create release
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: gh release create "$GITHUB_REF_NAME" --generate-notes
+  pypi-publish:
+    name: Upload release to PyPI
+    runs-on: ubuntu-latest
+    needs: [setup_release]
+    environment:
+      name: pypi
+      url: https://pypi.org/p/axolotl
+    permissions:
+      id-token: write  # IMPORTANT: this permission is mandatory for trusted publishing
+    steps:
+      - name: Check out repository code
+        uses: actions/checkout@v4
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Install dependencies
+        run: |
+          pip3 install wheel packaging==23.2
+          pip3 install --no-build-isolation -e .
+          pip3 install -r requirements-dev.txt -r requirements-tests.txt
+
+      - name: Extract tag name
+        id: tag
+        run: echo ::set-output name=TAG_NAME::$(echo $GITHUB_REF | cut -d / -f 3)
+
+      - name: Update version in setup.py
+        run: |
+          sed -i -E 's/version="([0-9.]+)",/version="${{ steps.tag.outputs.TAG_NAME }}",/g' setup.py
+
+      - name: Build a source dist
+        run: |
+          python setup.py sdist
+
+      - name: Publish package distributions to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

.github/workflows/tests-nightly.yml

@@ -0,0 +1,139 @@
+name: Tests Nightly against upstream main
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: '0 0 * * *'  # Runs at 00:00 UTC every day
+
+jobs:
+  pre-commit:
+    name: pre-commit
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+          cache: 'pip' # caching pip dependencies
+      - uses: pre-commit/action@v3.0.1
+        env:
+          SKIP: no-commit-to-branch
+
+  pytest:
+    name: PyTest
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      max-parallel: 2
+      matrix:
+        python_version: ["3.11"]
+        pytorch_version: ["2.4.1", "2.5.1", "2.6.0"]
+    timeout-minutes: 20
+
+    steps:
+      - name: Check out repository code
+        uses: actions/checkout@v4
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python_version }}
+          cache: 'pip' # caching pip dependencies
+
+      - name: upgrade pip
+        run: |
+          pip3 install --upgrade pip
+          pip3 install --upgrade packaging==23.2 setuptools==75.8.0 wheel
+
+      - name: Install PyTorch
+        run: |
+          pip3 install torch==${{ matrix.pytorch_version }} --index-url https://download.pytorch.org/whl/cpu
+
+      - name: Update requirements.txt
+        run: |
+          sed -i 's#^transformers.*#transformers @ git+https://github.com/huggingface/transformers.git@main#' requirements.txt
+          sed -i 's#^peft.*#peft @ git+https://github.com/huggingface/peft.git@main#' requirements.txt
+          sed -i 's#^accelerate.*#accelerate @ git+https://github.com/huggingface/accelerate.git@main#' requirements.txt
+          sed -i 's#^trl.*#trl @ git+https://github.com/huggingface/trl.git@main#' requirements.txt
+          sed -i 's#^datasets.*#datasets @ git+https://github.com/huggingface/datasets.git@main#' requirements.txt
+
+      - name: Install dependencies
+        run: |
+          pip3 install --upgrade pip
+          pip3 install --upgrade packaging==23.2
+          pip3 install --no-build-isolation -U -e .
+          python scripts/unsloth_install.py | sh
+          python scripts/cutcrossentropy_install.py | sh
+          pip3 install -r requirements-dev.txt -r requirements-tests.txt
+
+      - name: Make sure PyTorch version wasn't clobbered
+        run: |
+          python -c "import torch; assert '${{ matrix.pytorch_version }}' in torch.__version__"
+
+      - name: Ensure axolotl CLI was installed
+        run: |
+          axolotl --help
+
+      - name: Run tests
+        run: |
+          pytest -n8 --dist loadfile --ignore=tests/e2e/ --ignore=tests/patched/ tests/
+          pytest tests/patched/
+
+      - name: cleanup pip cache
+        run: |
+          find "$(pip cache dir)/http-v2" -type f -mtime +14 -exec rm {} \;
+
+  docker-e2e-tests:
+    if: github.repository_owner == 'axolotl-ai-cloud'
+    # this job needs to be run on self-hosted GPU runners...
+    runs-on: [self-hosted, modal]
+    timeout-minutes: 60
+    needs: [pre-commit, pytest]
+
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - cuda: 124
+            cuda_version: 12.4.1
+            python_version: "3.11"
+            pytorch: 2.4.1
+            num_gpus: 1
+            axolotl_extras:
+            nightly_build: "true"
+          - cuda: 124
+            cuda_version: 12.4.1
+            python_version: "3.11"
+            pytorch: 2.5.1
+            num_gpus: 1
+            axolotl_extras:
+            nightly_build: "true"
+          - cuda: 124
+            cuda_version: 12.4.1
+            python_version: "3.11"
+            pytorch: 2.6.0
+            num_gpus: 1
+            axolotl_extras:
+            nightly_build: "true"
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Install Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+      - name: Install Modal
+        run: |
+          python -m pip install --upgrade pip
+          pip install modal==0.71.8 jinja2
+      - name: Update env vars
+        run: |
+          echo "BASE_TAG=main-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV
+          echo "PYTORCH_VERSION=${{ matrix.pytorch}}" >> $GITHUB_ENV
+          echo "AXOLOTL_ARGS=${{ matrix.axolotl_args}}" >> $GITHUB_ENV
+          echo "AXOLOTL_EXTRAS=${{ matrix.axolotl_extras}}" >> $GITHUB_ENV
+          echo "CUDA=${{ matrix.cuda }}" >> $GITHUB_ENV
+          echo "N_GPUS=${{ matrix.num_gpus }}" >> $GITHUB_ENV
+          echo "NIGHTLY_BUILD=${{ matrix.nightly_build }}" >> $GITHUB_ENV
+      - name: Run tests job on Modal
+        run: |
+          modal run cicd.tests

.github/workflows/tests.yml

@@ -0,0 +1,279 @@
+name: Tests
+on:
+  # check on push/merge to main, PRs, and manual triggers
+  merge_group:
+  push:
+    branches:
+      - "main"
+    paths:
+      - '**.py'
+      - 'requirements.txt'
+      - '.github/workflows/*.yml'
+      - 'requirements-tests.txt'
+      - 'cicd/cicd.sh'
+      - 'cicd/Dockerfile.jinja'
+  pull_request:
+      paths:
+       - '**.py'
+       - 'requirements.txt'
+       - '.github/workflows/*.yml'
+       - 'requirements-tests.txt'
+       - 'cicd/cicd.sh'
+       - 'cicd/Dockerfile.jinja'
+  workflow_dispatch:
+
+# Cancel jobs on the same ref if a new one is triggered
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+
+jobs:
+  pre-commit:
+    name: pre-commit
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+          cache: 'pip' # caching pip dependencies
+      - uses: pre-commit/action@v3.0.1
+        env:
+          SKIP: no-commit-to-branch
+
+  pytest:
+    name: PyTest
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      max-parallel: 2
+      matrix:
+        python_version: ["3.11"]
+        pytorch_version: ["2.4.1", "2.5.1", "2.6.0"]
+    timeout-minutes: 20
+
+    steps:
+      - name: Check out repository code
+        uses: actions/checkout@v4
+
+      - name: Restore HF cache
+        id: hf-cache-restore
+        uses: actions/cache/restore@v4
+        with:
+          path: |
+            /home/runner/.cache/huggingface/hub/datasets--*
+            /home/runner/.cache/huggingface/hub/models--*
+          key: ${{ runner.os }}-hf-hub-cache-${{ hashFiles('**/conftest.py') }}
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python_version }}
+          cache: 'pip' # caching pip dependencies
+
+      - name: upgrade pip
+        run: |
+          pip3 install --upgrade pip
+          pip3 install --upgrade packaging==23.2 setuptools==75.8.0 wheel
+
+      - name: Install PyTorch
+        run: |
+          pip3 install torch==${{ matrix.pytorch_version }}
+
+      - name: Install dependencies
+        run: |
+          pip3 show torch
+          pip3 install --no-build-isolation -U -e .
+          python scripts/unsloth_install.py | sh
+          python scripts/cutcrossentropy_install.py | sh
+          pip3 install -r requirements-dev.txt -r requirements-tests.txt
+
+      - name: Make sure PyTorch version wasn't clobbered
+        run: |
+          python -c "import torch; assert '${{ matrix.pytorch_version }}' in torch.__version__"
+
+      - name: Ensure axolotl CLI was installed
+        run: |
+          axolotl --help
+
+      - name: Run tests
+        run: |
+          pytest -v -n8 --dist loadfile --ignore=tests/e2e/ --ignore=tests/patched/ --ignore=tests/cli/ tests/
+          pytest -v tests/patched/
+          pytest -v tests/cli/
+
+      - name: cleanup pip cache
+        run: |
+          find "$(pip cache dir)/http-v2" -type f -mtime +14 -exec rm {} \;
+
+      - name: Save HF cache
+        id: hf-cache
+        uses: actions/cache/save@v4
+        with:
+          path: |
+            /home/runner/.cache/huggingface/hub/datasets--*
+            /home/runner/.cache/huggingface/hub/models--*
+          key: ${{ steps.hf-cache-restore.outputs.cache-primary-key }}
+
+  pytest-sdist:
+    name: PyTest from Source Dist
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      max-parallel: 1
+      matrix:
+        python_version: ["3.11"]
+        pytorch_version: ["2.4.1", "2.5.1", "2.6.0"]
+    timeout-minutes: 20
+
+    steps:
+      - name: Check out repository code
+        uses: actions/checkout@v4
+
+      - name: Restore HF cache
+        id: hf-cache-restore
+        uses: actions/cache/restore@v4
+        with:
+          path: |
+            /home/runner/.cache/huggingface/hub/datasets--*
+            /home/runner/.cache/huggingface/hub/models--*
+          key: ${{ runner.os }}-hf-hub-cache-${{ hashFiles('**/conftest.py') }}
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python_version }}
+          cache: 'pip' # caching pip dependencies
+
+      - name: upgrade pip
+        run: |
+          pip3 install --upgrade pip
+          pip3 install --upgrade packaging==23.2 setuptools==75.8.0 setuptools_scm build wheel
+
+      - name: Install PyTorch
+        run: |
+          pip3 install torch==${{ matrix.pytorch_version }}
+
+      - name: Install dependencies
+        run: |
+          pip3 show torch
+          python -m build --no-isolation --sdist
+          pip3 install --no-build-isolation dist/axolotl*.tar.gz
+          python scripts/unsloth_install.py | sh
+          python scripts/cutcrossentropy_install.py | sh
+          pip3 install -r requirements-dev.txt -r requirements-tests.txt
+
+      - name: Make sure PyTorch version wasn't clobbered
+        run: |
+          python -c "import torch; assert '${{ matrix.pytorch_version }}' in torch.__version__"
+
+      - name: Ensure axolotl CLI was installed
+        run: |
+          axolotl --help
+
+      - name: Run tests
+        run: |
+          pytest -v -n8 --dist loadfile --ignore=tests/e2e/ --ignore=tests/patched/ --ignore=tests/cli/ tests/
+          pytest -v tests/patched/
+          pytest -v tests/cli/
+
+      - name: cleanup pip cache
+        run: |
+          find "$(pip cache dir)/http-v2" -type f -mtime +14 -exec rm {} \;
+
+      - name: Save HF cache
+        id: hf-cache
+        uses: actions/cache/save@v4
+        with:
+          path: |
+            /home/runner/.cache/huggingface/hub/datasets--*
+            /home/runner/.cache/huggingface/hub/models--*
+          key: ${{ steps.hf-cache-restore.outputs.cache-primary-key }}
+
+  docker-e2e-tests-1st:
+    if: ${{ ! contains(github.event.commits[0].message, '[skip e2e]') && github.repository_owner == 'axolotl-ai-cloud' }}
+    # this job needs to be run on self-hosted GPU runners...
+    runs-on: [self-hosted, modal]
+    timeout-minutes: 90
+    needs: [pre-commit, pytest, pytest-sdist]
+
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - cuda: 124
+            cuda_version: 12.4.1
+            python_version: "3.11"
+            pytorch: 2.5.1
+            num_gpus: 1
+            axolotl_extras: vllm
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Install Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+      - name: Install Modal
+        run: |
+          python -m pip install --upgrade pip
+          pip install modal==0.71.8 jinja2
+      - name: Update env vars
+        run: |
+          echo "BASE_TAG=main-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV
+          echo "PYTORCH_VERSION=${{ matrix.pytorch}}" >> $GITHUB_ENV
+          echo "AXOLOTL_ARGS=${{ matrix.axolotl_args}}" >> $GITHUB_ENV
+          echo "AXOLOTL_EXTRAS=${{ matrix.axolotl_extras}}" >> $GITHUB_ENV
+          echo "CUDA=${{ matrix.cuda }}" >> $GITHUB_ENV
+          echo "MODAL_IMAGE_BUILDER_VERSION=2024.10" >> $GITHUB_ENV
+          echo "N_GPUS=${{ matrix.num_gpus }}" >> $GITHUB_ENV
+      - name: Run tests job on Modal
+        run: |
+          modal run cicd.tests
+
+  docker-e2e-tests:
+    if: github.repository_owner == 'axolotl-ai-cloud'
+    # this job needs to be run on self-hosted GPU runners...
+    runs-on: [self-hosted, modal]
+    timeout-minutes: 90
+    needs: [pre-commit, pytest, docker-e2e-tests-1st]
+
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - cuda: 124
+            cuda_version: 12.4.1
+            python_version: "3.11"
+            pytorch: 2.4.1
+            num_gpus: 1
+            axolotl_extras:
+          - cuda: 124
+            cuda_version: 12.4.1
+            python_version: "3.11"
+            pytorch: 2.6.0
+            num_gpus: 1
+            axolotl_extras:
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Install Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+      - name: Install Modal
+        run: |
+          python -m pip install --upgrade pip
+          pip install modal==0.71.8 jinja2
+      - name: Update env vars
+        run: |
+          echo "BASE_TAG=main-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}" >> $GITHUB_ENV
+          echo "PYTORCH_VERSION=${{ matrix.pytorch}}" >> $GITHUB_ENV
+          echo "AXOLOTL_ARGS=${{ matrix.axolotl_args}}" >> $GITHUB_ENV
+          echo "AXOLOTL_EXTRAS=${{ matrix.axolotl_extras}}" >> $GITHUB_ENV
+          echo "CUDA=${{ matrix.cuda }}" >> $GITHUB_ENV
+          echo "MODAL_IMAGE_BUILDER_VERSION=2024.10" >> $GITHUB_ENV
+          echo "N_GPUS=${{ matrix.num_gpus }}" >> $GITHUB_ENV
+      - name: Run tests job on Modal
+        run: |
+          modal run cicd.tests

.gitignore

@@ -0,0 +1,192 @@
+**/axolotl.egg-info
+configs
+last_run_prepared/
+outputs
+.vscode
+_site/
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+venv3.10/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+
+# WandB
+# wandb creates a folder to store logs for training runs
+wandb
+
+# Runs
+lora-out/*
+qlora-out/*
+mlruns/*
+
+/.quarto/
+prepared-datasets/
+submit.sh
+*.out*
+
+# Quartodoc generated files
+objects.json
+site_libs/
+
+typings/
+out/
+
+# vim
+*.swp

.isort.cfg

@@ -0,0 +1,3 @@
+[settings]
+profile=black
+known_third_party=wandb,comet_ml

.mypy.ini

@@ -0,0 +1,54 @@
+[mypy]
+plugins = pydantic.mypy
+exclude = venv
+
+[mypy-alpaca_lora_4bit.*]
+ignore_missing_imports = True
+
+[mypy-axolotl.monkeypatch.*]
+ignore_errors = True
+
+[mypy-axolotl.models.mixtral.*]
+ignore_errors = True
+
+[mypy-axolotl.integrations.liger.models.*]
+ignore_errors = True
+
+[mypy-axolotl.models.phi.*]
+ignore_errors = True
+
+[mypy-flash_attn.*]
+ignore_missing_imports = True
+
+[mypy-huggingface_hub]
+ignore_missing_imports = True
+
+[mypy-transformers.*]
+ignore_missing_imports = True
+
+[mypy-peft]
+ignore_missing_imports = True
+
+[mypy-wandb]
+ignore_missing_imports = True
+
+[mypy-bitsandbytes]
+ignore_missing_imports = True
+
+[mypy-requests]
+ignore_missing_imports = True
+
+[mypy-datasets]
+ignore_missing_imports = True
+
+[mypy-fire]
+ignore_missing_imports = True
+
+[mypy-setuptools]
+ignore_missing_imports = True
+
+[mypy-addict]
+ignore_missing_imports = True
+
+[mypy-xformers.*]
+ignore_missing_imports = True

.pre-commit-config.yaml

@@ -0,0 +1,45 @@
+default_language_version:
+    python: python3
+
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+    -   id: check-yaml
+    -   id: end-of-file-fixer
+    -   id: trailing-whitespace
+    -   id: no-commit-to-branch
+        args: ['--branch', 'main']
+-   repo: https://github.com/psf/black
+    rev: 25.1.0
+    hooks:
+    -   id: black
+-   repo: https://github.com/pycqa/isort
+    rev: 6.0.1
+    hooks:
+      - id: isort
+-   repo: https://github.com/PyCQA/flake8
+    rev: 7.1.2
+    hooks:
+    - id: flake8
+-   repo: https://github.com/pylint-dev/pylint
+    rev: v3.3.6
+    hooks:
+    - id: pylint
+-   repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.15.0
+    hooks:
+    - id: mypy
+      additional_dependencies:
+        [
+            'types-PyYAML',
+            'pydantic>=2.5.3',
+        ]
+-   repo: https://github.com/PyCQA/bandit
+    rev: 1.8.3
+    hooks:
+    -   id: bandit
+        args: [
+            '--ini',
+            '.bandit',
+        ]

.pylintrc

@@ -0,0 +1,15 @@
+[MASTER]
+init-hook="from pylint.config import find_default_config_files; import sys; sys.path.append(next(find_default_config_files()).parent.as_posix())"
+
+[TYPECHECK]
+
+# List of members which are set dynamically and missed by Pylint inference
+# system, and so shouldn't trigger E1101 when accessed.
+generated-members=numpy.*, torch.*
+
+
+[pylint.messages_control]
+disable=missing-function-docstring, line-too-long, import-error,
+    too-many-arguments, too-many-locals, too-many-statements, too-many-branches, too-few-public-methods,
+    too-many-instance-attributes, fixme, import-outside-toplevel, logging-fstring-interpolation,
+    too-many-positional-arguments, possibly-used-before-assignment

FAQS.md

@@ -0,0 +1,7 @@
+# FAQs
+
+- Can you train StableLM with this? Yes, but only with a single GPU atm. Multi GPU support is coming soon! Just waiting on this [PR](https://github.com/huggingface/transformers/pull/22874)
+- Will this work with Deepspeed? That's still a WIP, but setting `export ACCELERATE_USE_DEEPSPEED=true` should work in some cases
+- `Error invalid argument at line 359 in file /workspace/bitsandbytes/csrc/pythonInterface.c`
+`/arrow/cpp/src/arrow/filesystem/s3fs.cc:2598:  arrow::fs::FinalizeS3 was not called even though S3 was initialized.`
+This could lead to a segmentation fault at exit. Try reinstalling bitsandbytes and transformers from source.

LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

MANIFEST.in

@@ -0,0 +1,5 @@
+include requirements.txt
+include README.md
+include LICENSE
+include src/setuptools_axolotl_dynamic_dependencies.py
+recursive-include axolotl *.py

README.md

@@ -1,58 +1,5 @@
----
-base_model: google/gemma-3-1b-it
-library_name: transformers
-model_name: finetune-demo-lora
-tags:
-- generated_from_trainer
-- trl
-- sft
-licence: license
----
+# Baseten Training Demo 
 
-# Model Card for finetune-demo-lora
+This is a demo of how to finetune a model using Baseten Training.
 
-This model is a fine-tuned version of [google/gemma-3-1b-it](https://huggingface.co/google/gemma-3-1b-it).
-It has been trained using [TRL](https://github.com/huggingface/trl).
-
-## Quick start
-
-```python
-from transformers import pipeline
-
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="rayraycano/finetune-demo-lora", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
-```
-
-## Training procedure
-
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/philipkiely-baseten/baseten-finetune-demo/runs/2tohi2fa) 
-
-
-This model was trained with SFT.
-
-### Framework versions
-
-- TRL: 0.15.1
-- Transformers: 4.50.0
-- Pytorch: 2.6.0+cu124
-- Datasets: 3.4.1
-- Tokenizers: 0.21.1
-
-## Citations
-
-
-
-Cite TRL as:
-    
-```bibtex
-@misc{vonwerra2022trl,
-	title        = {{TRL: Transformer Reinforcement Learning}},
-	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
-	year         = 2020,
-	journal      = {GitHub repository},
-	publisher    = {GitHub},
-	howpublished = {\url{https://github.com/huggingface/trl}}
-}
-```
+See the [Get Started](https://docs.baseten.com/get-started) guide to learn more about how to use Baseten Training.

TODO.md

@@ -0,0 +1,10 @@
+# todo list
+
+- [] Validation of parameters for combinations that won't work
+
+
+
+## things that are known not to work
+
+- FSDP offload and gradient_checkpointing - https://github.com/pytorch/pytorch/issues/82203
+- adamw_bnb_8bit doesn't play well with FSDP offload

adapter_config.json

@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "gate_proj",
-    "down_proj",
+    "k_proj",
+    "up_proj",
     "q_proj",
     "v_proj",
-    "k_proj",
-    "up_proj"
+    "o_proj",
+    "gate_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b938dfd2d98dfdc9e091d12591b2efcf79364ebc7da12fc49f31f4ec44390e14
+oid sha256:f071151423b65de415efa62ec47dc39d7072ce7e56eab9c173f884ab2c52da37
 size 113632496

checkpointing_lws.yml

@@ -0,0 +1,650 @@
+apiVersion: leaderworkerset.x-k8s.io/v1
+kind: LeaderWorkerSet
+metadata:
+  creationTimestamp: "2025-06-17T22:08:13Z"
+  generation: 1
+  labels:
+    app: baseten-training-job-vq0521w
+    baseten.co/job: "true"
+    domain: user
+    environment: production
+    instance_type: H100__2x44x240
+    org.identifier: raymond--cano--baseten--co
+    org.primary_key: B5W5OLP
+    training_job.id: vq0521w
+    training_project.id: jwdgnwk
+  name: baseten-training-job-vq0521w-multinode
+  namespace: org-9914a591b6e04ff7848a21ae64fa3398
+  resourceVersion: "236739712"
+  uid: fe987c78-34c1-44da-8b0f-64074e101724
+spec:
+  leaderWorkerTemplate:
+    leaderTemplate:
+      metadata:
+        labels:
+          app: baseten-training-job-vq0521w
+          baseten.co/job: "true"
+          baseten.co/job_type: training
+          domain: user
+          environment: production
+          instance_type: H100__2x44x240
+          org.identifier: raymond--cano--baseten--co
+          org.primary_key: B5W5OLP
+          training_job.id: vq0521w
+          training_project.id: jwdgnwk
+        name: baseten-training-job-vq0521w
+        namespace: org-9914a591b6e04ff7848a21ae64fa3398
+      spec:
+        affinity:
+          nodeAffinity:
+            preferredDuringSchedulingIgnoredDuringExecution:
+            - preference:
+                matchExpressions:
+                - key: baseten-internal/workload-type
+                  operator: In
+                  values:
+                  - training
+              weight: 100
+            - preference:
+                matchExpressions:
+                - key: baseten-internal/customer-reservation
+                  operator: Exists
+              weight: 90
+        automountServiceAccountToken: false
+        containers:
+        - command:
+          - sh
+          - -c
+          - |-
+            # NB(nikhil): We prevent excessive restarts:
+            #   1) If the job completed successfully, we use a sentinel file to sleep on next start
+            #   2) If the job is crashing, we use an attempt counter to track if we should start again
+            BT_RETRY_COUNT="${BT_RETRY_COUNT:-1}"
+            ATTEMPT_COUNT_FILE="/bt_state/attempt_count.txt"
+
+
+            if [ -f "/bt_state/completed.txt" ]; then
+              echo "Job already completed successfully, sleeping..."
+              sleep infinity
+            fi
+
+            attempt_count=0
+            if [ -f "$ATTEMPT_COUNT_FILE" ]; then
+              attempt_count="$(cat "$ATTEMPT_COUNT_FILE")"
+            fi
+
+            if [ "$attempt_count" -ge "$BT_RETRY_COUNT" ]; then
+              echo "Exceeded ${BT_RETRY_COUNT} retry limit with ${attempt_count} attempts, sleeping..."
+              sleep infinity
+            fi
+
+            # Increment attempt count across runs
+            attempt_count=$((attempt_count + 1))
+            echo "$attempt_count" > "$ATTEMPT_COUNT_FILE"
+
+            echo "Copying artifacts to ($PWD)"
+            cp -r /b10/workspace/* ./
+
+            EXIT_CODE=0
+            if [ "$EXIT_CODE" -eq 0 ]; then
+              /bin/sh -c './run.sh' || EXIT_CODE=$?
+            fi
+            completed_date=$(date +%s)
+            echo "Job has exited. Syncing checkpoints..."
+            while true; do
+              if [ -f "/bt_state/sync_start.txt" ]; then
+                sync_start_date=$(cat "/bt_state/sync_start.txt")
+                if [ "$sync_start_date" -gt "$completed_date" ]; then
+                  echo "Checkpoint sync completed."
+                  break
+                fi
+              fi
+              sleep 10
+            done
+
+            if [ "$EXIT_CODE" -eq 0 ]; then
+              touch "/bt_state/completed.txt"
+            fi
+
+            exit "$EXIT_CODE"
+          env:
+          - name: PYTHONUNBUFFERED
+            value: "1"
+          - name: IS_LOCAL_DEV
+            value: "False"
+          - name: BT_TRAINING_JOB_ID
+            value: vq0521w
+          - name: BT_RETRY_COUNT
+            value: "1"
+          - name: BASE_MODEL_ID
+            value: google/gemma-3-27b-it
+          - name: OUTPUT_LORA_REPO_ID
+            value: rayraycano/finetune-demo-lora
+          - name: HF_TOKEN
+            valueFrom:
+              secretKeyRef:
+                key: hf_access_token
+                name: baseten-oracles-secrets
+          - name: WANDB_API_KEY
+            valueFrom:
+              secretKeyRef:
+                key: wandb_api_key
+                name: baseten-oracles-secrets
+          - name: BT_NODE_RANK
+            valueFrom:
+              fieldRef:
+                fieldPath: metadata.labels['leaderworkerset.sigs.k8s.io/worker-index']
+          - name: BT_NUM_GPUS
+            value: "2"
+          - name: BT_LEADER_ADDR
+            value: $(LWS_LEADER_ADDRESS)
+          - name: BT_GROUP_SIZE
+            value: $(LWS_GROUP_SIZE)
+          - name: BT_RW_CACHE_DIR
+            value: /root/.cache/user_artifacts
+          - name: BT_CHECKPOINT_DIR
+            value: /mnt/ckpts
+          image: axolotlai/axolotl:main-20250324-py3.11-cu124-2.6.0
+          name: training-job-container
+          resources:
+            limits:
+              cpu: 43550m
+              ephemeral-storage: 800Gi
+              memory: 240354Mi
+              nvidia.com/gpu: "2"
+            requests:
+              cpu: 42800m
+              ephemeral-storage: 800Gi
+              memory: 239354Mi
+              nvidia.com/gpu: "2"
+          securityContext:
+            capabilities:
+              add:
+              - SYS_ADMIN
+              drop:
+              - CAP_NET_RAW
+              - CAP_NET_ADMIN
+          volumeMounts:
+          - mountPath: /lib/modules
+            name: host-modules
+            readOnly: true
+          - mountPath: /dev/fuse
+            name: fuse
+          - mountPath: /dev/shm
+            name: shm
+          - mountPath: /secrets
+            name: secrets
+            readOnly: true
+          - mountPath: /bt_state
+            name: bt-state
+          - mountPath: /b10/workspace
+            name: runtime-artifacts
+            readOnly: true
+          - mountPath: /root/.cache/user_artifacts
+            name: baseten-fs-rw-cache
+            subPath: jwdgnwk/user_artifacts
+          - mountPath: /root/.cache/huggingface
+            name: baseten-fs-rw-cache
+            subPath: jwdgnwk/huggingface
+          - mountPath: /mnt/ckpts
+            name: ckpt-shared-storage
+        - command:
+          - /bin/sh
+          - -c
+          - |
+            while [ ! -f "/bt_state/completed.txt" ]; do
+              start_time=$(date +%s)
+              # We reference these secrets explicitly because they might rotate during the job
+              export AWS_ACCESS_KEY_ID=$(cat /aws-secrets/aws_access_key_id)
+              export AWS_SECRET_ACCESS_KEY=$(cat /aws-secrets/aws_secret_access_key)
+              export AWS_SESSION_TOKEN=$(cat /aws-secrets/aws_session_token)
+              # dry run to provide visibility into what will be synced. This can be checked to verify that we aren't making duplicate syncs.
+              echo "======= Dry run to provide visibility into what will be synced ======="
+              aws s3 sync /mnt/ckpts s3://bt-training-b5w5olp-8de8b19b-6cba-465a-a5fe-d6e16b627cc5/training_projects/jwdgnwk/jobs/vq0521w/rank-$BT_NODE_RANK/ --dryrun
+              echo "======= Syncing checkpoints to S3 ======="
+              aws s3 sync /mnt/ckpts s3://bt-training-b5w5olp-8de8b19b-6cba-465a-a5fe-d6e16b627cc5/training_projects/jwdgnwk/jobs/vq0521w/rank-$BT_NODE_RANK/
+              # write the start time after writing. This helps ensure that we complete the sync
+              # that starts after the job has completed.
+              echo "$start_time" > "/bt_state/sync_start.txt"
+              sleep 30
+            done
+            exit 0
+          env:
+          - name: AWS_DEFAULT_REGION
+            value: us-west-2
+          - name: BT_NODE_RANK
+            valueFrom:
+              fieldRef:
+                fieldPath: metadata.labels['leaderworkerset.sigs.k8s.io/worker-index']
+          image: amazon/aws-cli:2.13.25
+          name: s3-sync-sidecar
+          resources:
+            limits:
+              cpu: 200m
+              memory: 512Mi
+            requests:
+              cpu: 100m
+              memory: 256Mi
+          volumeMounts:
+          - mountPath: /mnt/ckpts
+            name: ckpt-shared-storage
+          - mountPath: /bt_state
+            name: bt-state
+          - mountPath: /aws-secrets
+            name: aws-secrets
+            readOnly: true
+        initContainers:
+        - command:
+          - sh
+          - -c
+          - |
+            set -e
+            apk add --no-cache wget
+            echo "Downloading artifact 1"
+            wget -q "https://baseten-user-models-2971lo7k.s3.amazonaws.com/organizations/B5W5OLP/training/bea8e66c-d732-4b8b-b265-18c0bbfa506f/scripts.tgz?AWSAccessKeyId=AKIA4FWSEGGQU5RCDCKX&Signature=8xoXJZmRxjwXXJPh4FTLN17Wv%2BY%3D&Expires=1750201691" -O artifact-1.tar
+            echo "Extracting artifact 1"
+            tar -xvf artifact-1.tar -C /b10/workspace
+            rm artifact-1.tar
+          image: alpine:3.21.3
+          imagePullPolicy: IfNotPresent
+          name: fetch-runtime-artifacts
+          resources: {}
+          volumeMounts:
+          - mountPath: /b10/workspace
+            name: runtime-artifacts
+        - command:
+          - sh
+          - -c
+          - |
+            set -e
+            echo "Mounting RW cache"
+            cd /mnt
+            mkdir -p jwdgnwk/user_artifacts
+            mkdir -p jwdgnwk/huggingface
+          image: alpine:3.21.3
+          imagePullPolicy: IfNotPresent
+          name: rw-cache-init-container
+          resources: {}
+          volumeMounts:
+          - mountPath: /mnt
+            name: baseten-fs-rw-cache
+        nodeSelector:
+          baseten.co/gpu-type: nvidia-h100-80gb
+          nvidia.com/gpu.product: NVIDIA-H100-80GB-HBM3
+        priorityClassName: user-model-priority
+        serviceAccountName: baseten-user
+        tolerations:
+        - effect: NoSchedule
+          key: baseten-internal/customer-reservation
+          operator: Equal
+          value: raymond--cano--baseten--co
+        - effect: NoSchedule
+          key: baseten-internal/workload-type
+          operator: Equal
+          value: training
+        volumes:
+        - emptyDir:
+            medium: Memory
+            sizeLimit: 128Gi
+          name: shm
+        - name: secrets
+          secret:
+            secretName: baseten-oracles-secrets
+        - name: aws-secrets
+          secret:
+            secretName: baseten-training-checkpointing-secrets
+        - hostPath:
+            path: /lib/modules
+            type: Directory
+          name: host-modules
+        - hostPath:
+            path: /dev/fuse
+          name: fuse
+        - emptyDir:
+            medium: Memory
+            sizeLimit: 1Mi
+          name: bt-state
+        - emptyDir:
+            sizeLimit: 15Gi
+          name: runtime-artifacts
+        - name: baseten-fs-rw-cache
+          persistentVolumeClaim:
+            claimName: org-9914a591b6e04ff7848a21ae64fa3398-training-fs-pvc
+        - ephemeral:
+            volumeClaimTemplate:
+              metadata: {}
+              spec:
+                accessModes:
+                - ReadWriteOnce
+                resources:
+                  requests:
+                    storage: 1000Gi
+          name: ckpt-shared-storage
+    restartPolicy: None
+    size: 1
+    workerTemplate:
+      metadata:
+        labels:
+          app: baseten-training-job-vq0521w
+          baseten.co/job: "true"
+          baseten.co/job_type: training
+          domain: user
+          environment: production
+          instance_type: H100__2x44x240
+          org.identifier: raymond--cano--baseten--co
+          org.primary_key: B5W5OLP
+          training_job.id: vq0521w
+          training_project.id: jwdgnwk
+        name: baseten-training-job-vq0521w
+        namespace: org-9914a591b6e04ff7848a21ae64fa3398
+      spec:
+        affinity:
+          nodeAffinity:
+            preferredDuringSchedulingIgnoredDuringExecution:
+            - preference:
+                matchExpressions:
+                - key: baseten-internal/workload-type
+                  operator: In
+                  values:
+                  - training
+              weight: 100
+            - preference:
+                matchExpressions:
+                - key: baseten-internal/customer-reservation
+                  operator: Exists
+              weight: 90
+        automountServiceAccountToken: false
+        containers:
+        - command:
+          - sh
+          - -c
+          - |-
+            # NB(nikhil): We prevent excessive restarts:
+            #   1) If the job completed successfully, we use a sentinel file to sleep on next start
+            #   2) If the job is crashing, we use an attempt counter to track if we should start again
+            BT_RETRY_COUNT="${BT_RETRY_COUNT:-1}"
+            ATTEMPT_COUNT_FILE="/bt_state/attempt_count.txt"
+
+
+            if [ -f "/bt_state/completed.txt" ]; then
+              echo "Job already completed successfully, sleeping..."
+              sleep infinity
+            fi
+
+            attempt_count=0
+            if [ -f "$ATTEMPT_COUNT_FILE" ]; then
+              attempt_count="$(cat "$ATTEMPT_COUNT_FILE")"
+            fi
+
+            if [ "$attempt_count" -ge "$BT_RETRY_COUNT" ]; then
+              echo "Exceeded ${BT_RETRY_COUNT} retry limit with ${attempt_count} attempts, sleeping..."
+              sleep infinity
+            fi
+
+            # Increment attempt count across runs
+            attempt_count=$((attempt_count + 1))
+            echo "$attempt_count" > "$ATTEMPT_COUNT_FILE"
+
+            echo "Copying artifacts to ($PWD)"
+            cp -r /b10/workspace/* ./
+
+            EXIT_CODE=0
+            if [ "$EXIT_CODE" -eq 0 ]; then
+              /bin/sh -c './run.sh' || EXIT_CODE=$?
+            fi
+            completed_date=$(date +%s)
+            echo "Job has exited. Syncing checkpoints..."
+            while true; do
+              if [ -f "/bt_state/sync_start.txt" ]; then
+                sync_start_date=$(cat "/bt_state/sync_start.txt")
+                if [ "$sync_start_date" -gt "$completed_date" ]; then
+                  echo "Checkpoint sync completed."
+                  break
+                fi
+              fi
+              sleep 10
+            done
+
+            if [ "$EXIT_CODE" -eq 0 ]; then
+              touch "/bt_state/completed.txt"
+            fi
+
+            exit "$EXIT_CODE"
+          env:
+          - name: PYTHONUNBUFFERED
+            value: "1"
+          - name: IS_LOCAL_DEV
+            value: "False"
+          - name: BT_TRAINING_JOB_ID
+            value: vq0521w
+          - name: BT_RETRY_COUNT
+            value: "1"
+          - name: BASE_MODEL_ID
+            value: google/gemma-3-27b-it
+          - name: OUTPUT_LORA_REPO_ID
+            value: rayraycano/finetune-demo-lora
+          - name: HF_TOKEN
+            valueFrom:
+              secretKeyRef:
+                key: hf_access_token
+                name: baseten-oracles-secrets
+          - name: WANDB_API_KEY
+            valueFrom:
+              secretKeyRef:
+                key: wandb_api_key
+                name: baseten-oracles-secrets
+          - name: BT_NODE_RANK
+            valueFrom:
+              fieldRef:
+                fieldPath: metadata.labels['leaderworkerset.sigs.k8s.io/worker-index']
+          - name: BT_NUM_GPUS
+            value: "2"
+          - name: BT_LEADER_ADDR
+            value: $(LWS_LEADER_ADDRESS)
+          - name: BT_GROUP_SIZE
+            value: $(LWS_GROUP_SIZE)
+          - name: BT_RW_CACHE_DIR
+            value: /root/.cache/user_artifacts
+          - name: BT_CHECKPOINT_DIR
+            value: /mnt/ckpts
+          image: axolotlai/axolotl:main-20250324-py3.11-cu124-2.6.0
+          name: training-job-container
+          resources:
+            limits:
+              cpu: 43550m
+              ephemeral-storage: 800Gi
+              memory: 240354Mi
+              nvidia.com/gpu: "2"
+            requests:
+              cpu: 42800m
+              ephemeral-storage: 800Gi
+              memory: 239354Mi
+              nvidia.com/gpu: "2"
+          securityContext:
+            capabilities:
+              add:
+              - SYS_ADMIN
+              drop:
+              - CAP_NET_RAW
+              - CAP_NET_ADMIN
+          volumeMounts:
+          - mountPath: /lib/modules
+            name: host-modules
+            readOnly: true
+          - mountPath: /dev/fuse
+            name: fuse
+          - mountPath: /dev/shm
+            name: shm
+          - mountPath: /secrets
+            name: secrets
+            readOnly: true
+          - mountPath: /bt_state
+            name: bt-state
+          - mountPath: /b10/workspace
+            name: runtime-artifacts
+            readOnly: true
+          - mountPath: /root/.cache/user_artifacts
+            name: baseten-fs-rw-cache
+            subPath: jwdgnwk/user_artifacts
+          - mountPath: /root/.cache/huggingface
+            name: baseten-fs-rw-cache
+            subPath: jwdgnwk/huggingface
+          - mountPath: /mnt/ckpts
+            name: ckpt-shared-storage
+        - command:
+          - /bin/sh
+          - -c
+          - |-
+            while [ ! -f "/bt_state/completed.txt" ]; do
+              start_time=$(date +%s)
+              # We reference these secrets explicitly because they might rotate during the job
+              export AWS_ACCESS_KEY_ID=$(cat /aws-secrets/aws_access_key_id)
+              export AWS_SECRET_ACCESS_KEY=$(cat /aws-secrets/aws_secret_access_key)
+              export AWS_SESSION_TOKEN=$(cat /aws-secrets/aws_session_token)
+              # dry run to provide visibility into what will be synced. This can be checked to verify that we aren't making duplicate syncs.
+              echo "======= Dry run to provide visibility into what will be synced ======="
+              aws s3 sync /mnt/ckpts s3://bt-training-b5w5olp-8de8b19b-6cba-465a-a5fe-d6e16b627cc5/training_projects/jwdgnwk/jobs/vq0521w/rank-$BT_NODE_RANK/ --dryrun
+              echo "======= Syncing checkpoints to S3 ======="
+              aws s3 sync /mnt/ckpts s3://bt-training-b5w5olp-8de8b19b-6cba-465a-a5fe-d6e16b627cc5/training_projects/jwdgnwk/jobs/vq0521w/rank-$BT_NODE_RANK/
+              # write the start time after writing. This helps ensure that we complete the sync
+              # that starts after the job has completed.
+              echo "$start_time" > "/bt_state/sync_start.txt"
+              sleep 30
+            done
+            exit 0
+          env:
+          - name: AWS_DEFAULT_REGION
+            value: us-west-2
+          - name: BT_NODE_RANK
+            valueFrom:
+              fieldRef:
+                fieldPath: metadata.labels['leaderworkerset.sigs.k8s.io/worker-index']
+          image: amazon/aws-cli:2.13.25
+          name: s3-sync-sidecar
+          resources:
+            limits:
+              cpu: 200m
+              memory: 512Mi
+            requests:
+              cpu: 100m
+              memory: 256Mi
+          volumeMounts:
+          - mountPath: /mnt/ckpts
+            name: ckpt-shared-storage
+          - mountPath: /bt_state
+            name: bt-state
+          - mountPath: /aws-secrets
+            name: aws-secrets
+            readOnly: true
+        initContainers:
+        - command:
+          - sh
+          - -c
+          - |
+            set -e
+            apk add --no-cache wget
+            echo "Downloading artifact 1"
+            wget -q "https://baseten-user-models-2971lo7k.s3.amazonaws.com/organizations/B5W5OLP/training/bea8e66c-d732-4b8b-b265-18c0bbfa506f/scripts.tgz?AWSAccessKeyId=AKIA4FWSEGGQU5RCDCKX&Signature=8xoXJZmRxjwXXJPh4FTLN17Wv%2BY%3D&Expires=1750201691" -O artifact-1.tar
+            echo "Extracting artifact 1"
+            tar -xvf artifact-1.tar -C /b10/workspace
+            rm artifact-1.tar
+          image: alpine:3.21.3
+          imagePullPolicy: IfNotPresent
+          name: fetch-runtime-artifacts
+          resources: {}
+          volumeMounts:
+          - mountPath: /b10/workspace
+            name: runtime-artifacts
+        - command:
+          - sh
+          - -c
+          - |
+            set -e
+            echo "Mounting RW cache"
+            cd /mnt
+            mkdir -p jwdgnwk/user_artifacts
+            mkdir -p jwdgnwk/huggingface
+          image: alpine:3.21.3
+          imagePullPolicy: IfNotPresent
+          name: rw-cache-init-container
+          resources: {}
+          volumeMounts:
+          - mountPath: /mnt
+            name: baseten-fs-rw-cache
+        nodeSelector:
+          baseten.co/gpu-type: nvidia-h100-80gb
+          nvidia.com/gpu.product: NVIDIA-H100-80GB-HBM3
+        priorityClassName: user-model-priority
+        serviceAccountName: baseten-user
+        tolerations:
+        - effect: NoSchedule
+          key: baseten-internal/customer-reservation
+          operator: Equal
+          value: raymond--cano--baseten--co
+        - effect: NoSchedule
+          key: baseten-internal/workload-type
+          operator: Equal
+          value: training
+        volumes:
+        - emptyDir:
+            medium: Memory
+            sizeLimit: 128Gi
+          name: shm
+        - name: secrets
+          secret:
+            secretName: baseten-oracles-secrets
+        - name: aws-secrets
+          secret:
+            secretName: baseten-training-checkpointing-secrets
+        - hostPath:
+            path: /lib/modules
+            type: Directory
+          name: host-modules
+        - hostPath:
+            path: /dev/fuse
+          name: fuse
+        - emptyDir:
+            medium: Memory
+            sizeLimit: 1Mi
+          name: bt-state
+        - emptyDir:
+            sizeLimit: 15Gi
+          name: runtime-artifacts
+        - name: baseten-fs-rw-cache
+          persistentVolumeClaim:
+            claimName: org-9914a591b6e04ff7848a21ae64fa3398-training-fs-pvc
+        - ephemeral:
+            volumeClaimTemplate:
+              metadata: {}
+              spec:
+                accessModes:
+                - ReadWriteOnce
+                resources:
+                  requests:
+                    storage: 1000Gi
+          name: ckpt-shared-storage
+  networkConfig:
+    subdomainPolicy: Shared
+  replicas: 1
+  rolloutStrategy:
+    rollingUpdateConfiguration:
+      maxSurge: 0
+      maxUnavailable: 1
+    type: RollingUpdate
+  startupPolicy: LeaderReady
+status:
+  conditions:
+  - lastTransitionTime: "2025-06-17T22:08:13Z"
+    message: Replicas are progressing
+    reason: GroupsProgressing
+    status: "False"
+    type: Progressing
+  - lastTransitionTime: "2025-06-17T22:08:30Z"
+    message: All replicas are ready
+    reason: AllGroupsReady
+    status: "True"
+    type: Available
+  hpaPodSelector: leaderworkerset.sigs.k8s.io/name=baseten-training-job-vq0521w-multinode,leaderworkerset.sigs.k8s.io/worker-index=0
+  readyReplicas: 1
+  replicas: 1
+  updatedReplicas: 1

cicd/Dockerfile.jinja

@@ -0,0 +1,52 @@
+FROM axolotlai/axolotl-base:{{ BASE_TAG }}
+
+ENV TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6+PTX"
+ENV AXOLOTL_EXTRAS="{{ AXOLOTL_EXTRAS }}"
+ENV AXOLOTL_ARGS="{{ AXOLOTL_ARGS }}"
+ENV CUDA="{{ CUDA }}"
+ENV PYTORCH_VERSION="{{ PYTORCH_VERSION }}"
+ENV GITHUB_REF="{{ GITHUB_REF }}"
+ENV GITHUB_SHA="{{ GITHUB_SHA }}"
+ENV NIGHTLY_BUILD="{{ NIGHTLY_BUILD }}"
+ENV HF_HOME="{{ HF_HOME }}"
+
+RUN apt-get update && \
+    apt-get install -y --allow-change-held-packages vim curl nano libnccl2 libnccl-dev
+
+WORKDIR /workspace
+
+RUN git clone --depth=1 https://github.com/axolotl-ai-cloud/axolotl.git
+
+WORKDIR /workspace/axolotl
+
+RUN git fetch origin +$GITHUB_REF && \
+    git checkout FETCH_HEAD
+
+# If AXOLOTL_EXTRAS is set, append it in brackets
+RUN if [ "$NIGHTLY_BUILD" = "true" ] ; then \
+        sed -i 's#^transformers.*#transformers @ git+https://github.com/huggingface/transformers.git@main#' requirements.txt; \
+        sed -i 's#^peft.*#peft @ git+https://github.com/huggingface/peft.git@main#' requirements.txt; \
+        sed -i 's#^accelerate.*#accelerate @ git+https://github.com/huggingface/accelerate.git@main#' requirements.txt; \
+        sed -i 's#^trl.*#trl @ git+https://github.com/huggingface/trl.git@main#' requirements.txt; \
+        sed -i 's#^datasets.*#datasets @ git+https://github.com/huggingface/datasets.git@main#' requirements.txt; \
+    fi
+
+RUN pip install packaging==23.2 setuptools==75.8.0
+RUN if [ "$AXOLOTL_EXTRAS" != "" ] ; then \
+        pip install --no-build-isolation -e .[deepspeed,flash-attn,ring-flash-attn,optimizers,ray,$AXOLOTL_EXTRAS] $AXOLOTL_ARGS; \
+    else \
+        pip install --no-build-isolation -e .[deepspeed,flash-attn,ring-flash-attn,optimizers,ray] $AXOLOTL_ARGS; \
+    fi
+
+RUN python scripts/unsloth_install.py | sh
+RUN python scripts/cutcrossentropy_install.py | sh
+
+# So we can test the Docker image
+RUN pip install -r requirements-dev.txt -r requirements-tests.txt
+
+# fix so that git fetch/pull from remote works
+RUN git config remote.origin.fetch "+refs/heads/*:refs/remotes/origin/*" && \
+    git config --get remote.origin.fetch
+
+# helper for huggingface-login cli
+RUN git config --global credential.helper store

cicd/cicd.sh

@@ -0,0 +1,12 @@
+#!/bin/bash
+set -e
+
+python -c "import torch; assert '$PYTORCH_VERSION' in torch.__version__"
+
+pytest -v --durations=10 -n8 --ignore=tests/e2e/ --ignore=tests/patched/ --ignore=tests/cli /workspace/axolotl/tests/
+pytest -v --durations=10 /workspace/axolotl/tests/e2e/patched/lora_kernels  # running these with the other patches causes a failure
+pytest -v --durations=10 --ignore=tests/e2e/patched/lora_kernels /workspace/axolotl/tests/e2e/patched
+pytest -v --durations=10 -n1 /workspace/axolotl/tests/e2e/solo/
+pytest -v --durations=10 /workspace/axolotl/tests/e2e/integrations/
+pytest -v --durations=10 /workspace/axolotl/tests/cli
+pytest -v --durations=10 --ignore=tests/e2e/solo/ --ignore=tests/e2e/patched/ --ignore=tests/e2e/multigpu/ --ignore=tests/e2e/integrations/ --ignore=tests/cli /workspace/axolotl/tests/e2e/

cicd/multigpu.py

@@ -0,0 +1,82 @@
+"""
+modal application to run axolotl gpu tests in Modal
+"""
+
+# pylint: disable=duplicate-code
+
+import os
+import pathlib
+import tempfile
+
+import jinja2
+import modal
+from jinja2 import select_autoescape
+from modal import App, Image
+
+cicd_path = pathlib.Path(__file__).parent.resolve()
+
+template_loader = jinja2.FileSystemLoader(searchpath=cicd_path)
+template_env = jinja2.Environment(
+    loader=template_loader, autoescape=select_autoescape()
+)
+df_template = template_env.get_template("Dockerfile.jinja")
+
+df_args = {
+    "AXOLOTL_EXTRAS": os.environ.get("AXOLOTL_EXTRAS", ""),
+    "AXOLOTL_ARGS": os.environ.get("AXOLOTL_ARGS", ""),
+    "PYTORCH_VERSION": os.environ.get("PYTORCH_VERSION", "2.4.1"),
+    "BASE_TAG": os.environ.get("BASE_TAG", "main-base-py3.11-cu121-2.4.1"),
+    "CUDA": os.environ.get("CUDA", "121"),
+    "GITHUB_REF": os.environ.get("GITHUB_REF", "refs/heads/main"),
+    "GITHUB_SHA": os.environ.get("GITHUB_SHA", ""),
+    "HF_HOME": "/workspace/data/huggingface-cache/hub",
+}
+
+dockerfile_contents = df_template.render(**df_args)
+
+temp_dir = tempfile.mkdtemp()
+with open(pathlib.Path(temp_dir) / "Dockerfile", "w", encoding="utf-8") as f:
+    f.write(dockerfile_contents)
+
+cicd_image = Image.from_dockerfile(
+    pathlib.Path(temp_dir) / "Dockerfile",
+    force_build=True,
+    gpu="A10G",
+).env(df_args)
+
+app = App("Axolotl CI/CD", secrets=[])
+
+hf_cache_volume = modal.Volume.from_name(
+    "axolotl-ci-hf-hub-cache", create_if_missing=True
+)
+VOLUME_CONFIG = {
+    "/workspace/data/huggingface-cache/hub": hf_cache_volume,
+}
+
+N_GPUS = int(os.environ.get("N_GPUS", 2))
+GPU_CONFIG = modal.gpu.H100(count=N_GPUS)
+
+
+def run_cmd(cmd: str, run_folder: str):
+    import subprocess  # nosec
+
+    # Propagate errors from subprocess.
+    if exit_code := subprocess.call(cmd.split(), cwd=run_folder):  # nosec
+        exit(exit_code)  # pylint: disable=consider-using-sys-exit
+
+
+@app.function(
+    image=cicd_image,
+    gpu=GPU_CONFIG,
+    timeout=60 * 60,
+    cpu=8.0,
+    memory=131072 * N_GPUS,
+    volumes=VOLUME_CONFIG,
+)
+def cicd_pytest():
+    run_cmd("./cicd/multigpu.sh", "/workspace/axolotl")
+
+
+@app.local_entrypoint()
+def main():
+    cicd_pytest.remote()

cicd/multigpu.sh

@@ -0,0 +1,5 @@
+#!/bin/bash
+set -e
+
+# only run one test at a time so as not to OOM the GPU
+pytest -v -n2 /workspace/axolotl/tests/e2e/multigpu/

cicd/tests.py

@@ -0,0 +1,82 @@
+"""Modal app to run axolotl GPU tests"""
+
+# pylint: disable=duplicate-code
+
+import os
+import pathlib
+import tempfile
+
+import jinja2
+import modal
+from jinja2 import select_autoescape
+from modal import App, Image
+
+cicd_path = pathlib.Path(__file__).parent.resolve()
+
+template_loader = jinja2.FileSystemLoader(searchpath=cicd_path)
+template_env = jinja2.Environment(
+    loader=template_loader, autoescape=select_autoescape()
+)
+df_template = template_env.get_template("Dockerfile.jinja")
+
+df_args = {
+    "AXOLOTL_EXTRAS": os.environ.get("AXOLOTL_EXTRAS", ""),
+    "AXOLOTL_ARGS": os.environ.get("AXOLOTL_ARGS", ""),
+    "PYTORCH_VERSION": os.environ.get("PYTORCH_VERSION", "2.4.1"),
+    "BASE_TAG": os.environ.get("BASE_TAG", "main-base-py3.11-cu121-2.4.1"),
+    "CUDA": os.environ.get("CUDA", "121"),
+    "GITHUB_REF": os.environ.get("GITHUB_REF", "refs/heads/main"),
+    "GITHUB_SHA": os.environ.get("GITHUB_SHA", ""),
+    "NIGHTLY_BUILD": os.environ.get("NIGHTLY_BUILD", ""),
+    "HF_HOME": "/workspace/data/huggingface-cache/hub",
+}
+
+dockerfile_contents = df_template.render(**df_args)
+
+temp_dir = tempfile.mkdtemp()
+with open(pathlib.Path(temp_dir) / "Dockerfile", "w", encoding="utf-8") as f:
+    f.write(dockerfile_contents)
+
+cicd_image = Image.from_dockerfile(
+    pathlib.Path(temp_dir) / "Dockerfile",
+    context_mount=None,
+    force_build=True,
+    gpu="A10G",
+).env(df_args)
+
+app = App("Axolotl CI/CD", secrets=[])
+
+hf_cache_volume = modal.Volume.from_name(
+    "axolotl-ci-hf-hub-cache", create_if_missing=True
+)
+VOLUME_CONFIG = {
+    "/workspace/data/huggingface-cache/hub": hf_cache_volume,
+}
+
+N_GPUS = int(os.environ.get("N_GPUS", 1))
+GPU_CONFIG = modal.gpu.L40S(count=N_GPUS)
+
+
+def run_cmd(cmd: str, run_folder: str):
+    import subprocess  # nosec
+
+    # Propagate errors from subprocess.
+    if exit_code := subprocess.call(cmd.split(), cwd=run_folder):  # nosec
+        exit(exit_code)  # pylint: disable=consider-using-sys-exit
+
+
+@app.function(
+    image=cicd_image,
+    gpu=GPU_CONFIG,
+    timeout=60 * 60,
+    cpu=8.0,
+    memory=131072,
+    volumes=VOLUME_CONFIG,
+)
+def cicd_pytest():
+    run_cmd("./cicd/cicd.sh", "/workspace/axolotl")
+
+
+@app.local_entrypoint()
+def main():
+    cicd_pytest.remote()

config.py

@@ -0,0 +1,53 @@
+from truss_train import definitions
+from truss.base import truss_config
+
+
+"""
+Runtime provides runtime options for the training job. See the docs to learn more 
+about configuring Training Cache and Automatic Checkpointing.
+"""
+runtime = definitions.Runtime(
+    start_commands=[
+        "/bin/sh -c './run.sh'",
+    ],
+    environment_variables={
+        # Make sure these secrets are set in your Baseten Workspace
+        "HF_TOKEN": definitions.SecretReference(name="hf_access_token"),
+        "WANDB_API_KEY": definitions.SecretReference(name="wandb_api_key"),
+        "BASE_MODEL_ID": "google/gemma-3-27b-it",
+        "OUTPUT_LORA_REPO_ID": "rayraycano/finetune-demo-lora", # TODO: your HF Repo ID
+    },
+    enable_cache=True,
+    checkpointing_config=definitions.CheckpointingConfig(
+        enabled=False,
+    ),
+)
+
+"""
+Compute allows you to specify the hardware required for the training job. See the docs to learn more
+about configuring multinode training.
+"""
+compute = definitions.Compute(
+    accelerator=truss_config.AcceleratorSpec(
+        accelerator=truss_config.Accelerator.H100,
+        count=8,
+    ),
+    # node_count=2,
+)
+
+"""
+TrainingJob is the main configuration object for your training job. It includes the compute, runtime, and image.
+"""
+training_job = definitions.TrainingJob(
+    compute=compute,
+    runtime=runtime,
+    # axolotl image includes most of the dependencies you need for training
+    image=definitions.Image(base_image="axolotlai/axolotl:main-20250324-py3.11-cu124-2.6.0"),
+)
+
+"""
+TrainingProject is an organizational tool to group your training jobs.
+"""
+first_project = definitions.TrainingProject(name="finetune-demo-full-feature-cru-us-east1-prod-1", job=training_job)
+
+

deepspeed_config.yml

@@ -0,0 +1,21 @@
+compute_environment: LOCAL_MACHINE                                                                                                                                           
+debug: false
+deepspeed_config:
+  deepspeed_multinode_launcher: standard
+  offload_optimizer_device: none
+  offload_param_device: none
+  zero3_init_flag: true
+  zero3_save_16bit_model: true
+  zero_stage: 3
+distributed_type: DEEPSPEED
+downcast_bf16: 'no'
+machine_rank: 0
+main_training_function: main
+mixed_precision: bf16
+num_machines: 1
+rdzv_backend: static
+same_network: true
+tpu_env: []
+tpu_use_cluster: false
+tpu_use_sudo: false
+use_cpu: false

deepspeed_configs/zero1.json

@@ -0,0 +1,23 @@
+{
+  "zero_optimization": {
+    "stage": 1,
+    "overlap_comm": true
+  },
+  "bf16": {
+    "enabled": "auto"
+  },
+  "fp16": {
+    "enabled": "auto",
+    "auto_cast": false,
+    "loss_scale": 0,
+    "initial_scale_power": 32,
+    "loss_scale_window": 1000,
+    "hysteresis": 2,
+    "min_loss_scale": 1
+  },
+  "gradient_accumulation_steps": "auto",
+  "gradient_clipping": "auto",
+  "train_batch_size": "auto",
+  "train_micro_batch_size_per_gpu": "auto",
+  "wall_clock_breakdown": false
+}

deepspeed_configs/zero1_torch_compile.json

@@ -0,0 +1,27 @@
+{
+  "zero_optimization": {
+    "stage": 1,
+    "overlap_comm": true
+  },
+  "bf16": {
+    "enabled": "auto"
+  },
+  "fp16": {
+    "enabled": "auto",
+    "auto_cast": false,
+    "loss_scale": 0,
+    "initial_scale_power": 32,
+    "loss_scale_window": 1000,
+    "hysteresis": 2,
+    "min_loss_scale": 1
+  },
+  "compile": {
+    "disable": false,
+    "backend": "inductor"
+  },
+  "gradient_accumulation_steps": "auto",
+  "gradient_clipping": "auto",
+  "train_batch_size": "auto",
+  "train_micro_batch_size_per_gpu": "auto",
+  "wall_clock_breakdown": false
+}

deepspeed_configs/zero2.json

@@ -0,0 +1,27 @@
+{
+  "zero_optimization": {
+    "stage": 2,
+    "offload_optimizer": {
+      "device": "cpu"
+    },
+    "contiguous_gradients": true,
+    "overlap_comm": true
+  },
+  "bf16": {
+    "enabled": "auto"
+  },
+  "fp16": {
+    "enabled": "auto",
+    "auto_cast": false,
+    "loss_scale": 0,
+    "initial_scale_power": 32,
+    "loss_scale_window": 1000,
+    "hysteresis": 2,
+    "min_loss_scale": 1
+  },
+  "gradient_accumulation_steps": "auto",
+  "gradient_clipping": "auto",
+  "train_batch_size": "auto",
+  "train_micro_batch_size_per_gpu": "auto",
+  "wall_clock_breakdown": false
+}

deepspeed_configs/zero3.json

@@ -0,0 +1,31 @@
+{
+  "zero_optimization": {
+    "stage": 3,
+    "overlap_comm": true,
+    "contiguous_gradients": true,
+    "sub_group_size": 0,
+    "reduce_bucket_size": "auto",
+    "stage3_prefetch_bucket_size": "auto",
+    "stage3_param_persistence_threshold": "auto",
+    "stage3_max_live_parameters": 0,
+    "stage3_max_reuse_distance": 0,
+    "stage3_gather_16bit_weights_on_model_save": true
+  },
+  "bf16": {
+    "enabled": "auto"
+  },
+  "fp16": {
+    "enabled": "auto",
+    "auto_cast": false,
+    "loss_scale": 0,
+    "initial_scale_power": 32,
+    "loss_scale_window": 1000,
+    "hysteresis": 2,
+    "min_loss_scale": 1
+  },
+  "gradient_accumulation_steps": "auto",
+  "gradient_clipping": "auto",
+  "train_batch_size": "auto",
+  "train_micro_batch_size_per_gpu": "auto",
+  "wall_clock_breakdown": false
+}

deepspeed_configs/zero3_bf16.json

@@ -0,0 +1,22 @@
+{
+  "zero_optimization": {
+    "stage": 3,
+    "overlap_comm": true,
+    "contiguous_gradients": true,
+    "sub_group_size": 0,
+    "reduce_bucket_size": "auto",
+    "stage3_prefetch_bucket_size": "auto",
+    "stage3_param_persistence_threshold": "auto",
+    "stage3_max_live_parameters": 0,
+    "stage3_max_reuse_distance": 0,
+    "stage3_gather_16bit_weights_on_model_save": true
+  },
+  "bf16": {
+    "enabled": true
+  },
+  "gradient_accumulation_steps": "auto",
+  "gradient_clipping": "auto",
+  "train_batch_size": "auto",
+  "train_micro_batch_size_per_gpu": "auto",
+  "wall_clock_breakdown": false
+}