fix attetion mask with packing

make sure we eval for openorca
handle orca splits
2023-07-15 10:38:01 -04:00 · 2023-07-02 17:59:10 -04:00 · 2023-07-01 07:20:23 -04:00
99 changed files with 1218 additions and 6347 deletions
--- a/.github/CODE_OF_CONDUCT.md
+++ b/.github/CODE_OF_CONDUCT.md
@@ -1,129 +0,0 @@
-# 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.
--- a/.github/CONTRIBUTING.md
+++ b/.github/CONTRIBUTING.md
@@ -1,76 +0,0 @@
-# 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 Conductcode
-
-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/OpenAccess-AI-Collective/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/OpenAccess-AI-Collective/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/OpenAccess-AI-Collective/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/OpenAccess-AI-Collective/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!
--- a/.github/FUNDING.yml
+++ b/.github/FUNDING.yml
@@ -1,13 +0,0 @@
-# These are supported funding model platforms
-
-github: 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: # 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: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']
--- a/.github/ISSUE_TEMPLATE/bug-report.yaml
+++ b/.github/ISSUE_TEMPLATE/bug-report.yaml
@@ -1,105 +0,0 @@
-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/OpenAccess-AI-Collective/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: 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
--- a/.github/ISSUE_TEMPLATE/config.yml
+++ b/.github/ISSUE_TEMPLATE/config.yml
@@ -1,7 +0,0 @@
-blank_issues_enabled: false
-contact_links:
-  - name: Ask a question
-    url: https://github.com/OpenAccess-AI-Collective/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
--- a/.github/ISSUE_TEMPLATE/docs.yml
+++ b/.github/ISSUE_TEMPLATE/docs.yml
@@ -1,46 +0,0 @@
-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/OpenAccess-AI-Collective/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
--- a/.github/ISSUE_TEMPLATE/feature-request.yaml
+++ b/.github/ISSUE_TEMPLATE/feature-request.yaml
@@ -1,63 +0,0 @@
-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/OpenAccess-AI-Collective/axolotl/discussions/categories/ideas) didn't find any similar feature requests."
-          required: true
-        - label: "I searched previous [Issues](https://github.com/OpenAccess-AI-Collective/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
--- a/.github/PULL_REQUEST_TEMPLATE/pull_request_template_simple.md
+++ b/.github/PULL_REQUEST_TEMPLATE/pull_request_template_simple.md
@@ -1,22 +0,0 @@
-<!--- 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: -->
--- a/.github/SECURITY.md
+++ b/.github/SECURITY.md
@@ -1,9 +0,0 @@
-# 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.
--- a/.github/SUPPORT.md
+++ b/.github/SUPPORT.md
@@ -1,10 +0,0 @@
-# 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.
--- a/.github/workflows/base.yml
+++ b/.github/workflows/base.yml
@@ -18,13 +18,23 @@ jobs:
          - cuda: "118"
            cuda_version: 11.8.0
            python_version: "3.9"
-            pytorch: 2.0.1
-            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 9.0+PTX"
+            pytorch: 2.0.0
+            axolotl_extras:
          - cuda: "118"
            cuda_version: 11.8.0
            python_version: "3.10"
-            pytorch: 2.0.1
-            torch_cuda_arch_list: "7.0 7.5 8.0 8.6 9.0+PTX"
+            pytorch: 2.0.0
+            axolotl_extras:
+          - cuda: "117"
+            cuda_version: 11.7.1
+            python_version: "3.9"
+            pytorch: 1.13.1
+            axolotl_extras:
+          - cuda: "118"
+            cuda_version: 11.8.0
+            python_version: "3.9"
+            pytorch: 2.0.0
+            axolotl_extras: gptq
    steps:
      - name: Checkout
        uses: actions/checkout@v3
@@ -48,9 +58,11 @@ jobs:
          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: ${{ steps.metadata.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
          build-args: |
            CUDA_VERSION=${{ matrix.cuda_version }}
            CUDA=${{ matrix.cuda }}
            PYTHON_VERSION=${{ matrix.python_version }}
            PYTORCH_VERSION=${{ matrix.pytorch }}
-            TORCH_CUDA_ARCH_LIST=${{ matrix.torch_cuda_arch_list }}
+            AXOLOTL_EXTRAS=${{ matrix.axolotl_extras }}
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -4,6 +4,7 @@ on:
  push:
    branches:
      - "main"
+      - "dev"

 jobs:
  build-axolotl:
@@ -13,21 +14,26 @@ jobs:
      fail-fast: false
      matrix:
        include:
-          - cuda: 118
+          - cuda: cu118
            cuda_version: 11.8.0
            python_version: "3.9"
-            pytorch: 2.0.1
+            pytorch: 2.0.0
            axolotl_extras:
-          - cuda: 118
+          - cuda: cu118
            cuda_version: 11.8.0
            python_version: "3.10"
-            pytorch: 2.0.1
+            pytorch: 2.0.0
            axolotl_extras:
-          - cuda: 118
+          - cuda: cu118
            cuda_version: 11.8.0
            python_version: "3.9"
-            pytorch: 2.0.1
+            pytorch: 2.0.0
            axolotl_extras: gptq
+          - cuda: cu117
+            cuda_version: 11.7.1
+            python_version: "3.9"
+            pytorch: 1.13.1
+            axolotl_extras:
    runs-on: self-hosted
    steps:
      - name: Checkout
@@ -49,12 +55,13 @@ jobs:
        with:
          context: .
          build-args: |
-            BASE_TAG=${{ github.ref_name }}-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}
-            CUDA=${{ matrix.cuda }}
+            BASE_TAG=${{ github.ref_name }}-base-py${{ matrix.python_version }}-${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
          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 }}
+          tags: ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
          labels: ${{ steps.metadata.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
  build-axolotl-runpod:
    needs: build-axolotl
    if: github.repository_owner == 'OpenAccess-AI-Collective'
@@ -62,22 +69,26 @@ jobs:
    strategy:
      matrix:
        include:
-          - cuda: 118
+          - cuda: cu118
            cuda_version: 11.8.0
            python_version: "3.9"
-            pytorch: 2.0.1
+            pytorch: 2.0.0
            axolotl_extras:
-          - cuda: 118
+          - cuda: cu118
            cuda_version: 11.8.0
            python_version: "3.10"
-            pytorch: 2.0.1
+            pytorch: 2.0.0
            axolotl_extras:
-            is_latest: true
-          - cuda: 118
+          - cuda: cu118
            cuda_version: 11.8.0
            python_version: "3.9"
-            pytorch: 2.0.1
+            pytorch: 2.0.0
            axolotl_extras: gptq
+          - cuda: cu117
+            cuda_version: 11.7.1
+            python_version: "3.9"
+            pytorch: 1.13.1
+            axolotl_extras:
    runs-on: self-hosted
    steps:
      - name: Checkout
@@ -99,11 +110,10 @@ jobs:
        with:
          context: .
          build-args: |
-            BASE_TAG=${{ github.ref_name }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
-            CUDA=${{ matrix.cuda }}
+            BASE_TAG=${{ github.ref_name }}-py${{ matrix.python_version }}-${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
          file: ./docker/Dockerfile-runpod
          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) || '' }}
+          tags: ${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
          labels: ${{ steps.metadata.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
--- a/.github/workflows/tests.yml
+++ b/.github/workflows/tests.yml
@@ -24,7 +24,7 @@ jobs:

      - name: Install dependencies
        run: |
-          pip install -e .[peft]
+          pip install -e .
          pip install -r requirements-tests.txt

      - name: Run tests
--- a/202
+++ b/202
@@ -1,202 +0,0 @@
-
-                                 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.
--- a/README.md
+++ b/README.md
@@ -1,40 +1,10 @@
 # Axolotl

-Axolotl is a tool designed to streamline the fine-tuning of various AI models, offering support for multiple configurations and architectures.
-
-<table>
-<tr>
-<td>
-
-## Table of Contents
- [Introduction](#axolotl)
- [Supported Features](#axolotl-supports)
- [Quickstart](#quickstart-)
- [Installation](#installation)
-  - [Docker Installation](#environment)
-  - [Conda/Pip venv Installation](#condapip-venv)
-  - [LambdaLabs Installation](#lambdalabs)
- [Dataset](#dataset)
-  - [How to Add Custom Prompts](#how-to-add-custom-prompts)
-  - [How to Use Custom Pretokenized Dataset](#how-to-use-your-custom-pretokenized-dataset)
- [Config](#config)
-  - [Train](#train)
-  - [Inference](#inference)
-  - [Merge LORA to Base](#merge-lora-to-base)
- [Common Errors](#common-errors-)
- [Need Help?](#need-help-)
- [Badge](#badge-)
- [Community Showcase](#community-showcase)
- [Contributing](#contributing-)
-
-</td>
-<td>
-
 <div align="center">
  <img src="image/axolotl.png" alt="axolotl" width="160">
  <div>
    <p>
-      <b>Axolotl provides a unified repository for fine-tuning <br />a variety of AI models with ease</b>
+      <b>One repo to finetune them all! </b>
    </p>
    <p>
      Go ahead and axolotl questions!!
@@ -44,36 +14,30 @@ Axolotl is a tool designed to streamline the fine-tuning of various AI models, o
  </div>
 </div>

-</td>
-</tr>
-</table>
-
 ## Axolotl supports

-|          | fp16/fp32 | lora | qlora | gptq | gptq w/flash attn | flash attn | xformers attn |
-|----------|:----------|:-----|-------|------|-------------------|------------|---------------|
-| llama    | ✅         | ✅    | ✅     | ✅             | ✅                 | ✅          | ✅             |
-| Pythia   | ✅         | ✅    | ✅     | ❌             | ❌                 | ❌          | ❓             |
-| cerebras | ✅         | ✅    | ✅     | ❌             | ❌                 | ❌          | ❓             |
-| mpt      | ✅         | ❌    | ❓     | ❌             | ❌                 | ❌          | ❓             |
-| falcon   | ✅         | ✅    | ✅     | ❌             | ❌                 | ❌          | ❓             |
-| gpt-j    | ✅         | ✅    | ✅     | ❌             | ❌                 | ❓          | ❓             |
-| XGen     | ✅         | ❓    | ✅     | ❓             | ❓                 | ❓          | ✅             |
+|          | fp16/fp32 | lora | qlora | gptq | gptq w/ lora | gptq w/flash attn | flash attn | xformers attn |
+|----------|:----------|:-----|-------|------|:-------------|-------------------|------------|---------------|
+| llama    | ✅         | ✅    | ✅     | ✅    | ✅             | ✅                 | ✅          | ✅             |
+| Pythia   | ✅         | ✅    | ✅     | ❌    | ❓            | ❌                 | ❌          | ❓             |
+| cerebras | ✅         | ✅    | ✅     | ❌    | ❓            | ❌                 | ❌          | ✅             |
+| mpt      | ✅         | ❌    | ❓     | ❌    | ❓            | ❌                 | ❌          | ❓             |
+| falcon   | ✅         | ✅    | ✅     | ❌    | ❓            | ❌                 | ❌          | ✅             |
+| gpt-j    | ✅         | ✅    | ✅     | ❌    | ❓            | ❌                 | ❓          | ✅             |


 ## Quickstart ⚡

-Get started with Axolotl in just a few steps! This quickstart guide will walk you through setting up and running a basic fine-tuning task.
-
-**Requirements**: Python >=3.9 and Pytorch >=2.0.
+**Requirements**: Python 3.9 and Pytorch 2.0.

 ```bash
 git clone https://github.com/OpenAccess-AI-Collective/axolotl
-cd axolotl

-pip3 install -e .[flash-attn]
+pip3 install -e .
 pip3 install -U git+https://github.com/huggingface/peft.git

+accelerate config
+
 # finetune lora
 accelerate launch scripts/finetune.py examples/openllama-3b/lora.yml

@@ -88,10 +52,11 @@ accelerate launch scripts/finetune.py examples/openllama-3b/lora.yml \

 - Docker
  ```bash
-  docker run --gpus '"all"' --rm -it winglian/axolotl:main-py3.10-cu118-2.0.1
+  docker run --gpus '"all"' --rm -it winglian/axolotl:main-py3.9-cu118-2.0.0
  ```
-  - `winglian/axolotl-runpod:main-py3.10-cu118-2.0.1`: for runpod
-  - `winglian/axolotl-runpod:main-py3.9-cu118-2.0.1-gptq`: for gptq
+  - `winglian/axolotl-runpod:main-py3.9-cu118-2.0.0`: for runpod
+  - `winglian/axolotl-runpod:main-py3.9-cu118-2.0.0-gptq`: for gptq
+  - `winglian/axolotl:dev`: dev branch (not usually up to date)

  Or run on the current files for development:

@@ -100,7 +65,7 @@ accelerate launch scripts/finetune.py examples/openllama-3b/lora.yml \
  ```

 - Conda/Pip venv
-  1. Install python >=**3.9**
+  1. Install python **3.9**

  2. Install pytorch stable https://pytorch.org/get-started/locally/

@@ -143,7 +108,7 @@ accelerate launch scripts/finetune.py examples/openllama-3b/lora.yml \

  3. Install torch
  ```bash
-  pip3 install -U torch --index-url https://download.pytorch.org/whl/cu118
+  pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
  ```

  4. Axolotl
@@ -153,7 +118,9 @@ accelerate launch scripts/finetune.py examples/openllama-3b/lora.yml \

  pip3 install -e . # change depend on needs
  pip3 install protobuf==3.20.3
-  pip3 install -U --ignore-installed requests Pillow psutil scipy
+  pip3 install -U requests
+  pip3 install -U --ignore-installed psutil
+  pip3 install -U scipy
  pip3 install git+https://github.com/huggingface/peft.git # not for gptq
  ```

@@ -163,18 +130,15 @@ accelerate launch scripts/finetune.py examples/openllama-3b/lora.yml \
  ```
  </details>

- Windows: Please use WSL or Docker!
-
 ### Dataset

-Axolotl supports a variety of dataset formats. Below are some of the formats you can use.
 Have dataset(s) in one of the following format (JSONL recommended):

 - `alpaca`: instruction; input(optional)
  ```json
  {"instruction": "...", "input": "...", "output": "..."}
  ```
- `sharegpt:chat`: conversations where `from` is `human`/`gpt`
+- `sharegpt:chat`: conversations
  ```json
  {"conversations": [{"from": "...", "value": "..."}]}
  ```
@@ -259,18 +223,10 @@ Have dataset(s) in one of the following format (JSONL recommended):
  ```json
  {"conversations": [{"role": "...", "value": "..."}]}
  ```
- `metharme`: instruction, adds additional eos tokens
-  ```json
-  {"prompt": "...", "generation": "..."}
-  ```
 - `sharegpt_simple.load_role`: conversations where `role` is used instead of `from`
  ```json
  {"conversations": [{"role": "...", "value": "..."}]}
  ```
- `sharegpt_simple.load_guanaco`: conversations where `from` is `prompter`/`assistant` instead of default sharegpt
-  ```json
-  {"conversations": [{"from": "...", "value": "..."}]}
-  ```
 - `sharegpt_jokes`: creates a chat where bot is asked to tell a joke, then explain why the joke is funny
  ```json
  {"conversations": [{"title": "...", "text": "...", "explanation": "..."}]}
@@ -280,34 +236,16 @@ Have dataset(s) in one of the following format (JSONL recommended):

 #### How to add custom prompts

-Using yaml. Example:
-```yaml
-datasets:
-  - path: repo
-    type:
-      system_prompt: ""
-      no_input_format: |-
-        User: {instruction}<|end_of_turn|>
-        Assistant:
-      format: |-
-        User: {instruction}
-        {input}<|end_of_turn|>
-        Assistant:
-```
+  1. Add your method to a file in [prompt_strategies](src/axolotl/prompt_strategies). Please see other files as example.
+  2. Use your custom file name as the dataset type.

-Using file:
-1. Add your method to a file in [prompt_strategies](src/axolotl/prompt_strategies). Please see other files as example.
-2. Use your custom file name as the dataset type `<prompt_strategies_file>.load_<load_fn>`.
+Optionally, download some datasets, see [data/README.md](data/README.md)

-#### How to use your custom pretokenized dataset
-
- Do not pass a `type:`
- Dataset must contain `input_ids`, `attention_mask`, `labels` in columns


 ### Config

-See [examples](examples) for quick start. It is recommended to duplicate and modify to your needs. The most important options are:
+See sample configs in [configs](configs) folder or [examples](examples) for quick start. It is recommended to duplicate and modify to your needs. The most important options are:

 - model
  ```yaml
@@ -317,33 +255,10 @@ See [examples](examples) for quick start. It is recommended to duplicate and mod

 - dataset
  ```yaml
-  sequence_len: 2048 # max token length for prompt
-
-  # huggingface repo
  datasets:
-    - path: vicgalle/alpaca-gpt4
+    - path: vicgalle/alpaca-gpt4 # local or huggingface repo
      type: alpaca # format from earlier
-
-  # huggingface repo with specific configuration/subset
-  datasets:
-    - path: EleutherAI/pile
-      name: enron_emails
-      type: completion # format from earlier
-
-  # huggingface repo with multiple named configurations/subsets
-  datasets:
-    - path: bigcode/commitpackft
-      name:
-        - ruby
-        - python
-        - typescript
-      type: ... # unimplemented custom format
-
-  # local
-  datasets:
-    - path: data.jsonl # or json
-      ds_type: json # see other options below
-      type: alpaca
+  sequence_len: 2048 # max token length / prompt
  ```

 - loading
@@ -382,8 +297,6 @@ base_model_ignore_patterns:
 # if the base_model repo on hf hub doesn't include configuration .json files,
 # you can set that here, or leave this empty to default to base_model
 base_model_config: ./llama-7b-hf
-# you can specify to choose a specific model revision from huggingface hub
-model_revision:
 # Optional tokenizer configuration override in case you want to use a different tokenizer
 # than the one defined in the base model
 tokenizer_config:
@@ -395,11 +308,6 @@ tokenizer_type: AutoTokenizer
 trust_remote_code:
 # use_fast option for tokenizer loading from_pretrained, default to True
 tokenizer_use_fast:
-# Whether to use the legacy tokenizer setting, defaults to True
-tokenizer_legacy:
-# resize the model embeddings when new tokens are added to multiples of 32
-# this is reported to improve training speed on some models
-resize_token_embeddings_to_32x:

 # whether you are training a 4-bit GPTQ quantized model
 gptq: true
@@ -418,38 +326,14 @@ fp16: true
 # Use CUDA tf32
 tf32: true # require >=ampere

-# No AMP (automatic mixed precision)
-bfloat16: true # require >=ampere
-float16: true
-
 # a list of one or more datasets to finetune the model with
 datasets:
-  # hf dataset repo | "json" for local dataset, make sure to fill data_files
+  # this can be either a hf dataset, or relative path
  - path: vicgalle/alpaca-gpt4
  # The type of prompt to use for training. [alpaca, sharegpt, gpteacher, oasst, reflection]
-    type: alpaca # format | format:<prompt_style> (chat/instruct) | <prompt_strategies>.load_<load_fn>
-    ds_type: # Optional[str] (json|arrow|parquet) defines the datatype when path is a file
+    type: alpaca # format OR format:prompt_style (chat/instruct)
    data_files: # path to source data files
    shards: # number of shards to split data into
-    name: # name of dataset configuration to load
-
-  # custom user prompt
-  - path: repo
-    type:
-      # the below are defaults. only set what's needed.
-      system_prompt: ""
-      field_system: system
-      field_instruction: instruction
-      field_output: input
-
-      # customizable to be single line or multi-line
-      system_format: "{system}"
-      # 'format' can include {input}
-      format: |-
-        User: {instruction} {input}
-        Assistant:
-      # 'no_input_format' cannot include {input}
-      no_input_format: "{instruction} "

 # axolotl attempts to save the dataset as an arrow after packing the data together so
 # subsequent training attempts load faster, relative path
@@ -457,14 +341,11 @@ dataset_prepared_path: data/last_run_prepared
 # push prepared dataset to hub
 push_dataset_to_hub: # repo path
 # push checkpoints to hub
-hub_model_id: # repo path to push finetuned model
-# how to push checkpoints to hub
-# https://huggingface.co/docs/transformers/v4.31.0/en/main_classes/trainer#transformers.TrainingArguments.hub_strategy
-hub_strategy:
+push_to_hub_model_id: # repo path
 # whether to use hf `use_auth_token` for loading datasets. Useful for fetching private datasets
 # required to be true when used in combination with `push_dataset_to_hub`
 hf_use_auth_token: # boolean
-# How much of the dataset to set aside as evaluation. 1 = 100%, 0.50 = 50%, etc. 0 for no eval.
+# How much of the dataset to set aside as evaluation. 1 = 100%, 0.50 = 50%, etc
 val_set_size: 0.04
 # Num shards for whole dataset
 dataset_shard_num:
@@ -474,19 +355,9 @@ dataset_shard_idx:
 # the maximum length of an input to train with, this should typically be less than 2048
 # as most models have a token/context limit of 2048
 sequence_len: 2048
-# pad inputs so each step uses constant sized buffers
-# this will reduce memory fragmentation and may prevent OOMs, by re-using memory more efficiently
-pad_to_sequence_len:
 # max sequence length to concatenate training samples together up to
 # inspired by StackLLaMA. see https://huggingface.co/blog/stackllama#supervised-fine-tuning
-# FutureWarning: This will soon be DEPRECATED
 max_packed_sequence_len: 1024
-# use efficient multi-packing with block diagonal attention and per sequence position_ids. Recommend set to 'true'
-sample_packing:
-# you can set these packing optimizations AFTER starting a training at least once.
-# The trainer will provide recommended values for these values.
-sample_packing_eff_est:
-total_num_tokens:

 # if you want to use 'lora' or 'qlora' or leave blank to train all parameters in original model
 adapter: lora
@@ -511,19 +382,12 @@ lora_modules_to_save:
 lora_out_dir:
 lora_fan_in_fan_out: false

-# ReLoRA configuration
-# must use either 'lora' or 'qlora' adapter, and does not support fsdp or deepspeed
-relora_steps: # number of steps per ReLoRA restart
-relora_warmup_steps: # number of per-restart warmup steps
-relora_cpu_offload: # true to perform lora weight merges on cpu during restarts, for modest gpu memory savings
-
 # wandb configuration if you're using it
-wandb_mode: # "offline" to save run metadata locally and not sync to the server, "disabled" to turn off wandb
-wandb_project: # your wandb project name
-wandb_entity: # a wandb Team name if using a Team
+wandb_mode:
+wandb_project:
 wandb_watch:
-wandb_run_id: # set the name of your wandb run
-wandb_log_model: # "checkpoint" to log model to wandb Artifacts every `save_steps` or "end" to log only at the end of training
+wandb_run_id:
+wandb_log_model: # 'checkpoint'

 # where to save the finished model to
 output_dir: ./completed-model
@@ -535,22 +399,13 @@ eval_batch_size: 2
 num_epochs: 3
 warmup_steps: 100
 learning_rate: 0.00003
-lr_quadratic_warmup:
 logging_steps:
-save_strategy: # set to `no` to skip checkpoint saves
-save_steps: # leave empty to save at each epoch
-eval_steps: # leave empty to eval at each epoch
-save_total_limit: # checkpoints saved at a time
-max_steps:
-
-# save model as safetensors (require safetensors package)
-save_safetensors:
+save_steps:
+eval_steps:

 # whether to mask out or include the human's prompt from the training labels
 train_on_inputs: false
-# group similarly sized data to minimize padding
-# may be slower to start, as it must download and sort the entire dataset
-# note that training loss may have an oscillating pattern with this enabled
+# don't use this, leads to wonky training (according to someone on the internet)
 group_by_length: false

 # Whether to use gradient checkpointing https://huggingface.co/docs/transformers/v4.18.0/en/performance#gradient-checkpointing
@@ -586,8 +441,8 @@ max_grad_norm:
 flash_optimum:
 # whether to use xformers attention patch https://github.com/facebookresearch/xformers:
 xformers_attention:
-# whether to use flash attention patch https://github.com/Dao-AILab/flash-attention:
-flash_attention:
+# whether to use flash attention patch https://github.com/HazyResearch/flash-attention:
+flash_attention:  # require a100 for llama
 # whether to use scaled-dot-product attention
 # https://pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html
 sdp_attention:
@@ -596,10 +451,6 @@ landmark_attention:
 # xpos RoPE see https://github.com/kaiokendev/cutoff-len-is-context-len/blob/main/util/xpos_rope_llama_monkey_patch.py
 # llama only
 xpos_rope:
-# RoPE Scaling https://github.com/huggingface/transformers/pull/24653
-rope_scaling:
-  type: # linear | dynamic
-  factor: # float

 # resume from a specific checkpoint dir
 resume_from_checkpoint:
@@ -622,19 +473,14 @@ tokens:
 fsdp:
 fsdp_config:

-# Deepspeed config path
+# Deepspeed
 deepspeed:

-# Advanced DDP Arguments
-ddp_timeout:
-ddp_bucket_cap_mb:
-ddp_broadcast_buffers:
-
 # Path to torch distx for optim 'adamw_anyprecision'
 torchdistx_path:

-# Set to HF dataset for type: 'completion' for streaming instead of pre-tokenize
-pretraining_dataset:
+# Set padding for data collator to 'longest'
+collator_pad_to_longest:

 # Debug mode
 debug:
@@ -648,48 +494,22 @@ strict:

 </details>

+### Accelerate
+
+Configure accelerate
+
+```bash
+accelerate config
+
+# Edit manually
+# nano ~/.cache/huggingface/accelerate/default_config.yaml
+```
+
 ### Train

 Run
 ```bash
-accelerate launch scripts/finetune.py your_config.yml
-```
-
-#### Multi-GPU
-
-You can optionally pre-tokenize dataset with the following before finetuning:
-```bash
-CUDA_VISIBLE_DEVICES="" accelerate ... --prepare_ds_only
-```
-
-##### Config
-
- llama FSDP
-```yaml
-fsdp:
-  - full_shard
-  - auto_wrap
-fsdp_config:
-  fsdp_offload_params: true
-  fsdp_state_dict_type: FULL_STATE_DICT
-  fsdp_transformer_layer_cls_to_wrap: LlamaDecoderLayer
-```
-
- llama Deepspeed
-```yaml
-deepspeed: deepspeed/zero3.json
-```
-
-##### Weights & Biases Logging
-
- wandb options
-```yaml
-wandb_mode:
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_run_id:
-wandb_log_model:
+accelerate launch scripts/finetune.py configs/your_config.yml
 ```

 ### Inference
@@ -726,7 +546,7 @@ CUDA_VISIBLE_DEVICES="" python3 scripts/finetune.py ...

 ## Common Errors 🧰

-> If you encounter a 'Cuda out of memory' error, it means your GPU ran out of memory during the training process. Here's how to resolve it:
+> Cuda out of memory

 Please reduce any below
  - `micro_batch_size`
@@ -734,12 +554,6 @@ Please reduce any below
  - `gradient_accumulation_steps`
  - `sequence_len`

-> `failed (exitcode: -9)`
-
-Usually means your system has run out of system memory.
-Similarly, you should consider reducing the same settings as when you run out of VRAM.
-Additionally, look into upgrading your system RAM which should be simpler than GPU upgrades.
-
 > RuntimeError: expected scalar type Float but found Half

 Try set `fp16: true`
@@ -748,10 +562,6 @@ Try set `fp16: true`

 Try to turn off xformers.

-> accelerate config missing
-
-It's safe to ignore it.
-
 ## Need help? 🙋♂️

 Join our [Discord server](https://discord.gg/HhrNrHJPRb) where we can help you
@@ -768,8 +578,6 @@ Building something cool with Axolotl? Consider adding a badge to your model card

 ## Community Showcase

-Check out some of the projects and models that have been built using Axolotl! Have a model you'd like to add to our Community Showcase? Open a PR with your model.
-
 Open Access AI Collective
 - [Minotaur 13b](https://huggingface.co/openaccess-ai-collective/minotaur-13b)
 - [Manticore 13b](https://huggingface.co/openaccess-ai-collective/manticore-13b)
@@ -780,9 +588,7 @@ PocketDoc Labs

 ## Contributing 🤝

-Please read the [contributing guide](./.github/CONTRIBUTING.md)
-
-Bugs? Please check the [open issues](https://github.com/OpenAccess-AI-Collective/axolotl/issues/bug) else create a new Issue.
+Bugs? Please check for open issue else create a new [Issue](https://github.com/OpenAccess-AI-Collective/axolotl/issues/new).

 PRs are **greatly welcome**!

--- a/data/README.md
+++ b/data/README.md
@@ -0,0 +1,24 @@
+
+## Download some datasets
+```shell
+curl https://raw.githubusercontent.com/tloen/alpaca-lora/main/alpaca_data_gpt4.json -o data/raw/alpaca_data_gpt4.json
+curl https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json -L -o data/raw/vicuna_cleaned.json
+curl https://github.com/teknium1/GPTeacher/blob/main/Instruct/gpt4-instruct-similarity-0.6-dataset.json?raw=true -L -o data/raw/gpt4-instruct-similarity-0.6-dataset.json
+curl https://github.com/teknium1/GPTeacher/blob/main/Roleplay/roleplay-similarity_0.6-instruct-dataset.json?raw=true -L -o data/raw/roleplay-similarity_0.6-instruct-dataset.json
+```
+
+## Convert the JSON data files to JSONL.
+
+```shell
+python3 ./scripts/alpaca_json_to_jsonl.py --file data/alpaca_data_gpt4.json --output data/alpaca_data_gpt4.jsonl
+python3 ./scripts/alpaca_json_to_jsonl.py --file data/raw/vicuna_cleaned.json --output data/vicuna_cleaned.jsonl
+python3 ./scripts/alpaca_json_to_jsonl.py --file data/raw/roleplay-similarity_0.6-instruct-dataset.json --output data/roleplay-similarity_0.6-instruct-dataset.jsonl
+python3 ./scripts/alpaca_json_to_jsonl.py --file data/raw/gpt4-instruct-similarity-0.6-dataset.json --output data/gpt4-instruct-similarity-0.6-dataset.jsonl
+```
+---
+
+Using JSONL makes it easier to subset the data if you want a smaller training set, i.e get 2000 random examples.
+
+```shell
+shuf -n2000 data/vicuna_cleaned.jsonl > data/vicuna_cleaned.subset0.jsonl
+```
--- a/data/raw/.gitignore
+++ b/data/raw/.gitignore
@@ -0,0 +1 @@
+**
--- a/deepspeed/zero2.json
+++ b/deepspeed/zero2.json
@@ -1,46 +0,0 @@
-{
-    "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
-    },
-    "optimizer": {
-      "type": "AdamW",
-      "params": {
-        "lr": "auto",
-        "betas": [
-          0.9,
-          0.999
-        ],
-        "eps": 1e-8,
-        "weight_decay": "auto"
-      }
-    },
-    "scheduler": {
-      "type": "WarmupDecayLR",
-      "params": {
-        "warmup_min_lr": "auto",
-        "warmup_max_lr": "auto",
-        "warmup_num_steps": "auto",
-        "total_num_steps": "auto"
-      }
-    },
-    "train_batch_size": "auto",
-    "train_micro_batch_size_per_gpu": "auto",
-    "wall_clock_breakdown": false
-}
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -3,28 +3,24 @@ FROM winglian/axolotl-base:$BASE_TAG

 ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6+PTX"
 ARG AXOLOTL_EXTRAS=""
-ARG CUDA="118"
-ENV BNB_CUDA_VERSION=$CUDA

 RUN apt-get update && \
    apt-get install -y vim curl

 WORKDIR /workspace

-RUN pip3 install "peft @ git+https://github.com/huggingface/peft.git@main"
+RUN pip3 install --force-reinstall "peft @ git+https://github.com/huggingface/peft.git@main" \
+            "accelerate @ git+https://github.com/huggingface/accelerate.git@main" \
+            "transformers @ git+https://github.com/huggingface/transformers.git@main"
+
 RUN git clone --depth=1 https://github.com/OpenAccess-AI-Collective/axolotl.git
 # If AXOLOTL_EXTRAS is set, append it in brackets
 RUN cd axolotl && \
    if [ "$AXOLOTL_EXTRAS" != "" ] ; then \
-        pip install -e .[flash-attn,$AXOLOTL_EXTRAS]; \
+        pip install -e .[$AXOLOTL_EXTRAS]; \
    else \
-        pip install -e .[flash-attn]; \
+        pip install -e .; \
    fi

-# fix so that git fetch/pull from remote works
-RUN cd axolotl && \
-    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
--- a/docker/Dockerfile-base
+++ b/docker/Dockerfile-base
@@ -8,7 +8,7 @@ FROM nvidia/cuda:$CUDA_VERSION-cudnn$CUDNN_VERSION-devel-ubuntu$UBUNTU_VERSION a
 ENV PATH="/root/miniconda3/bin:${PATH}"

 ARG PYTHON_VERSION="3.9"
-ARG PYTORCH_VERSION="2.0.1"
+ARG PYTORCH="2.0.0"
 ARG CUDA="118"

 ENV PYTHON_VERSION=$PYTHON_VERSION
@@ -29,11 +29,30 @@ ENV PATH="/root/miniconda3/envs/py${PYTHON_VERSION}/bin:${PATH}"
 WORKDIR /workspace

 RUN python3 -m pip install --upgrade pip && pip3 install packaging && \
-    python3 -m pip install --no-cache-dir -U torch==${PYTORCH_VERSION}+cu${CUDA} --extra-index-url https://download.pytorch.org/whl/cu$CUDA
+    python3 -m pip install --no-cache-dir -U torch==${PYTORCH} torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu$CUDA
+
+
+FROM base-builder AS flash-attn-builder
+
+WORKDIR /workspace
+
+ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6+PTX"
+
+RUN git clone https://github.com/HazyResearch/flash-attention.git && \
+    cd flash-attention && \
+    python3 setup.py bdist_wheel && \
+    cd csrc/fused_dense_lib && \
+    python3 setup.py bdist_wheel && \
+    cd ../xentropy && \
+    python3 setup.py bdist_wheel && \
+    cd ../rotary && \
+    python3 setup.py bdist_wheel && \
+    cd ../layer_norm && \
+    python3 setup.py bdist_wheel

 FROM base-builder AS deepspeed-builder

-ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 9.0+PTX"
+ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6+PTX"

 WORKDIR /workspace

@@ -54,9 +73,6 @@ RUN git clone https://github.com/TimDettmers/bitsandbytes.git && \

 FROM base-builder

-ARG TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 9.0+PTX"
-ENV TORCH_CUDA_ARCH_LIST=$TORCH_CUDA_ARCH_LIST
-
 # recompile apex
 RUN python3 -m pip uninstall -y apex
 RUN git clone https://github.com/NVIDIA/apex
@@ -70,10 +86,15 @@ RUN mkdir -p /workspace/wheels/bitsandbytes
 COPY --from=deepspeed-builder /workspace/DeepSpeed/dist/deepspeed-*.whl wheels
 COPY --from=bnb-builder /workspace/bitsandbytes/dist/bitsandbytes-*.whl wheels
 COPY --from=bnb-builder /workspace/bitsandbytes/bitsandbytes/libbitsandbytes*.so wheels/bitsandbytes
+COPY --from=flash-attn-builder /workspace/flash-attention/dist/flash_attn-*.whl wheels
+COPY --from=flash-attn-builder /workspace/flash-attention/csrc/fused_dense_lib/dist/fused_dense_lib-*.whl wheels
+COPY --from=flash-attn-builder /workspace/flash-attention/csrc/xentropy/dist/xentropy_cuda_lib-*.whl wheels
+COPY --from=flash-attn-builder /workspace/flash-attention/csrc/rotary/dist/rotary_emb-*.whl wheels
+COPY --from=flash-attn-builder /workspace/flash-attention/csrc/layer_norm/dist/dropout_layer_norm-*.whl wheels

-RUN pip3 install wheels/deepspeed-*.whl
+RUN pip3 install wheels/deepspeed-*.whl wheels/flash_attn-*.whl wheels/fused_dense_lib-*.whl wheels/xentropy_cuda_lib-*.whl wheels/rotary_emb-*.whl wheels/dropout_layer_norm-*.whl
 RUN cd /workspace/builds/bitsandbytes && python3 setup.py install
 RUN git lfs install --skip-repo
 RUN pip3 install awscli && \
    # The base image ships with `pydantic==1.8.2` which is not working
-    pip3 install -U --no-cache-dir pydantic==1.10.10
+    pip3 install -U --no-cache-dir pydantic
--- a/docker/Dockerfile-runpod
+++ b/docker/Dockerfile-runpod
@@ -1,10 +1,6 @@
 ARG BASE_TAG=main
 FROM winglian/axolotl:$BASE_TAG

-ENV HF_DATASETS_CACHE="/workspace/data/huggingface-cache/datasets"
-ENV HUGGINGFACE_HUB_CACHE="/workspace/data/huggingface-cache/hub"
-ENV TRANSFORMERS_CACHE="/workspace/data/huggingface-cache/hub"
-
 COPY scripts/runpod-entrypoint.sh /root/runpod-entrypoint.sh

 RUN apt install --yes --no-install-recommends openssh-server tmux && \
--- a/deepspeed/zero3.json
+++ b/deepspeed/zero3.json
@@ -35,17 +35,20 @@
    "type": "AdamW",
    "params": {
      "lr": "auto",
-      "betas": "auto",
+      "betas": [
+        0.9,
+        0.999
+      ],
      "eps": 1e-8,
      "weight_decay": "auto"
    }
  },
  "scheduler": {
-    "type": "WarmupLR",
+    "type": "OneCycle",
    "params": {
-      "warmup_min_lr": "auto",
-      "warmup_max_lr": "auto",
-      "warmup_num_steps": "auto"
+      "cycle_min_lr": 0.00001,
+      "cycle_max_lr": 0.00003,
+      "cycle_first_step_size": 120
    }
  },
  "train_batch_size": "auto",
--- a/examples/cerebras/qlora.yml
+++ b/examples/cerebras/qlora.yml
@@ -23,7 +23,6 @@ lora_target_modules:
 lora_target_linear:
 lora_fan_in_fan_out:
 wandb_project:
-wandb_entity:
 wandb_watch:
 wandb_run_id:
 wandb_log_model:
@@ -36,7 +35,7 @@ torchdistx_path:
 lr_scheduler: cosine
 learning_rate: 0.0002
 train_on_inputs: false
-group_by_length: false
+group_by_length: true
 bf16: true
 fp16: false
 tf32: true
--- a/examples/code-llama/13b/lora.yml
+++ b/examples/code-llama/13b/lora.yml
@@ -1,67 +0,0 @@
-base_model: codellama/CodeLlama-13b-hf
-base_model_config: codellama/CodeLlama-13b-hf
-model_type: LlamaForCausalLM
-tokenizer_type: CodeLlamaTokenizer
-is_llama_derived_model: true
-
-load_in_8bit: true
-load_in_4bit: false
-strict: false
-
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.01
-output_dir: ./lora-out
-
-sequence_len: 100000
-sample_packing: true
-
-adapter: lora
-lora_model_dir:
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_run_id:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 2
-num_epochs: 3
-optimizer: adamw_bnb_8bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-warmup_steps: 10
-eval_steps: 20
-save_steps:
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "</s>"
-  unk_token: "<unk>"
--- a/examples/code-llama/13b/qlora.yml
+++ b/examples/code-llama/13b/qlora.yml
@@ -1,69 +0,0 @@
-base_model: codellama/CodeLlama-13b-hf
-base_model_config: codellama/CodeLlama-13b-hf
-model_type: LlamaForCausalLM
-tokenizer_type: CodeLlamaTokenizer
-is_llama_derived_model: true
-
-load_in_8bit: false
-load_in_4bit: true
-strict: false
-
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.01
-output_dir: ./qlora-out
-
-adapter: qlora
-lora_model_dir:
-
-sequence_len: 100000
-sample_packing: true
-
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_modules:
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_run_id:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 2
-num_epochs: 3
-optimizer: paged_adamw_32bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-warmup_steps: 10
-eval_steps: 20
-save_steps:
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "</s>"
-  unk_token: "<unk>"
--- a/examples/code-llama/34b/lora.yml
+++ b/examples/code-llama/34b/lora.yml
@@ -1,67 +0,0 @@
-base_model: codellama/CodeLlama-34b-hf
-base_model_config: codellama/CodeLlama-34b-hf
-model_type: LlamaForCausalLM
-tokenizer_type: CodeLlamaTokenizer
-is_llama_derived_model: true
-
-load_in_8bit: true
-load_in_4bit: false
-strict: false
-
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.01
-output_dir: ./lora-out
-
-sequence_len: 100000
-sample_packing: true
-
-adapter: lora
-lora_model_dir:
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_run_id:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 2
-num_epochs: 3
-optimizer: adamw_bnb_8bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-warmup_steps: 10
-eval_steps: 20
-save_steps:
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "</s>"
-  unk_token: "<unk>"
--- a/examples/code-llama/34b/qlora.yml
+++ b/examples/code-llama/34b/qlora.yml
@@ -1,69 +0,0 @@
-base_model: codellama/CodeLlama-34b-hf
-base_model_config: codellama/CodeLlama-34b-hf
-model_type: LlamaForCausalLM
-tokenizer_type: CodeLlamaTokenizer
-is_llama_derived_model: true
-
-load_in_8bit: false
-load_in_4bit: true
-strict: false
-
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.01
-output_dir: ./qlora-out
-
-adapter: qlora
-lora_model_dir:
-
-sequence_len: 100000
-sample_packing: true
-
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_modules:
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_run_id:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 2
-num_epochs: 3
-optimizer: paged_adamw_32bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-warmup_steps: 10
-eval_steps: 20
-save_steps:
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "</s>"
-  unk_token: "<unk>"
--- a/examples/code-llama/7b/lora.yml
+++ b/examples/code-llama/7b/lora.yml
@@ -1,67 +0,0 @@
-base_model: codellama/CodeLlama-7b-hf
-base_model_config: codellama/CodeLlama-7b-hf
-model_type: LlamaForCausalLM
-tokenizer_type: CodeLlamaTokenizer
-is_llama_derived_model: true
-
-load_in_8bit: true
-load_in_4bit: false
-strict: false
-
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.01
-output_dir: ./lora-out
-
-sequence_len: 100000
-sample_packing: true
-
-adapter: lora
-lora_model_dir:
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_run_id:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 2
-num_epochs: 3
-optimizer: adamw_bnb_8bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-warmup_steps: 10
-eval_steps: 20
-save_steps:
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "</s>"
-  unk_token: "<unk>"
--- a/examples/code-llama/7b/qlora.yml
+++ b/examples/code-llama/7b/qlora.yml
@@ -1,69 +0,0 @@
-base_model: codellama/CodeLlama-7b-hf
-base_model_config: codellama/CodeLlama-7b-hf
-model_type: LlamaForCausalLM
-tokenizer_type: CodeLlamaTokenizer
-is_llama_derived_model: true
-
-load_in_8bit: false
-load_in_4bit: true
-strict: false
-
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.01
-output_dir: ./qlora-out
-
-adapter: qlora
-lora_model_dir:
-
-sequence_len: 100000
-sample_packing: true
-
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_modules:
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_run_id:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 2
-num_epochs: 3
-optimizer: paged_adamw_32bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-warmup_steps: 10
-eval_steps: 20
-save_steps:
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "</s>"
-  unk_token: "<unk>"
--- a/examples/code-llama/README.md
+++ b/examples/code-llama/README.md
@@ -1,22 +0,0 @@
-# Overview
-
-This is an example of CodeLLaMA configuration for 7b, 13b and 34b.
-
-The 7b variant fits on any 24GB VRAM GPU and will take up about 17 GB of VRAM during training if using qlora and 20 GB if using lora. On a RTX 4090 it trains 3 epochs of the default dataset in about 15 minutes.
-
-The 13b variant will fit if you change these settings to these values:
-gradient_accumulation_steps: 2
-micro_batch_size: 1
-
-The 34b variant does not fit on 24GB of VRAM - you will need something with +40 gb VRAM that also supports flash attention v2 - A6000 or A100 are good choices.
-
-```shell
-accelerate launch scripts/finetune.py examples/code-llama/[MODEL_SIZE]/qlora.yml
-
-```
-or
-
-```shell
-accelerate launch scripts/finetune.py examples/code-llama/[MODEL_SIZE]/lora.yml
-
-```
--- a/examples/falcon/config-7b-lora.yml
+++ b/examples/falcon/config-7b-lora.yml
@@ -24,7 +24,6 @@ lora_target_modules:
 lora_target_linear: true
 lora_fan_in_fan_out:
 wandb_project:
-wandb_entity:
 wandb_watch:
 wandb_run_id:
 wandb_log_model:
--- a/examples/falcon/config-7b-qlora.yml
+++ b/examples/falcon/config-7b-qlora.yml
@@ -38,7 +38,6 @@ lora_target_linear: true
 lora_fan_in_fan_out:

 wandb_project:
-wandb_entity:
 wandb_watch:
 wandb_run_id:
 wandb_log_model:
--- a/examples/falcon/config-7b.yml
+++ b/examples/falcon/config-7b.yml
@@ -24,7 +24,6 @@ lora_target_modules:
 lora_target_linear: true
 lora_fan_in_fan_out:
 wandb_project:
-wandb_entity:
 wandb_watch:
 wandb_run_id:
 wandb_log_model:
--- a/examples/gptj/qlora.yml
+++ b/examples/gptj/qlora.yml
@@ -20,7 +20,6 @@ lora_target_modules:
 lora_target_linear: true
 lora_fan_in_fan_out:
 wandb_project:
-wandb_entity:
 wandb_watch:
 wandb_run_id:
 wandb_log_model:
@@ -33,7 +32,7 @@ torchdistx_path:
 lr_scheduler: cosine
 learning_rate: 0.0001
 train_on_inputs: false
-group_by_length: false
+group_by_length: true
 bf16: true
 fp16: false
 tf32: true
--- a/examples/gptq-lora-7b/config.yml
+++ b/examples/gptq-lora-7b/config.yml
@@ -22,7 +22,6 @@ lora_target_modules:
  - v_proj
 lora_fan_in_fan_out: false
 wandb_project: llama-7b-lora-int4
-wandb_entity:
 wandb_watch:
 wandb_run_id:
 wandb_log_model:
@@ -57,7 +56,7 @@ weight_decay: 0.0001
 fsdp:
 fsdp_config:
 tokens:
-  pad_token: "<pad>"
+  pad_token: "[PAD]"
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"
--- a/examples/jeopardy-bot/config.yml
+++ b/examples/jeopardy-bot/config.yml
@@ -18,7 +18,6 @@ lora_dropout:
 lora_target_modules:
 lora_fan_in_fan_out: false
 wandb_project:
-wandb_entity:
 wandb_watch:
 wandb_run_id:
 wandb_log_model:
--- a/examples/llama-2/README.md
+++ b/examples/llama-2/README.md
@@ -1,20 +0,0 @@
-# Overview
-
-This is an example of a llama-2 configuration for 7b and 13b. The yaml file contains configuration for the 7b variant, but you can just aswell use the same settings for 13b.
-
-The 7b variant fits on any 24GB VRAM GPU and will take up about 17 GB of VRAM during training if using qlora and 20 GB if using lora. On a RTX 4090 it trains 3 epochs of the default dataset in about 15 minutes.
-
-The 13b variant will fit if you change these settings to these values:
-gradient_accumulation_steps: 2
-micro_batch_size: 1
-
-```shell
-accelerate launch scripts/finetune.py examples/llama-2/qlora.yml
-
-```
-or
-
-```shell
-accelerate launch scripts/finetune.py examples/llama-2/lora.yml
-
-```
--- a/examples/llama-2/lora.yml
+++ b/examples/llama-2/lora.yml
@@ -1,67 +0,0 @@
-base_model: meta-llama/Llama-2-7b-hf
-base_model_config: meta-llama/Llama-2-7b-hf
-model_type: LlamaForCausalLM
-tokenizer_type: LlamaTokenizer
-is_llama_derived_model: true
-
-load_in_8bit: true
-load_in_4bit: false
-strict: false
-
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.01
-output_dir: ./lora-out
-
-sequence_len: 4096
-sample_packing: true
-
-adapter: lora
-lora_model_dir:
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_run_id:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 2
-num_epochs: 3
-optimizer: adamw_bnb_8bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-warmup_steps: 10
-eval_steps: 20
-save_steps:
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "</s>"
-  unk_token: "<unk>"
--- a/examples/llama-2/qlora.yml
+++ b/examples/llama-2/qlora.yml
@@ -1,69 +0,0 @@
-base_model: meta-llama/Llama-2-7b-hf
-base_model_config: meta-llama/Llama-2-7b-hf
-model_type: LlamaForCausalLM
-tokenizer_type: LlamaTokenizer
-is_llama_derived_model: true
-
-load_in_8bit: false
-load_in_4bit: true
-strict: false
-
-datasets:
-  - path: mhenrichsen/alpaca_2k_test
-    type: alpaca
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.01
-output_dir: ./qlora-out
-
-adapter: qlora
-lora_model_dir:
-
-sequence_len: 4096
-sample_packing: true
-
-lora_r: 32
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_modules:
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_run_id:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 2
-num_epochs: 3
-optimizer: paged_adamw_32bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-warmup_steps: 10
-eval_steps: 20
-save_steps:
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "</s>"
-  unk_token: "<unk>"
--- a/examples/llama-2/relora.yml
+++ b/examples/llama-2/relora.yml
@@ -1,73 +0,0 @@
-base_model: meta-llama/Llama-2-7b-hf
-base_model_config: meta-llama/Llama-2-7b-hf
-model_type: LlamaForCausalLM
-tokenizer_type: LlamaTokenizer
-is_llama_derived_model: true
-
-load_in_8bit: false
-load_in_4bit: true
-strict: false
-
-datasets:
-  - path: teknium/GPT4-LLM-Cleaned
-    type: alpaca
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.01
-output_dir: ./relora-out
-
-adapter: qlora
-lora_model_dir:
-
-sequence_len: 4096
-sample_packing: true
-
-lora_r: 8
-lora_alpha: 16
-lora_dropout: 0.05
-lora_target_modules:
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-relora_steps: 150
-relora_warmup_steps: 10
-relora_cpu_offload: false
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_run_id:
-wandb_log_model:
-
-gradient_accumulation_steps: 4
-micro_batch_size: 4
-num_epochs: 3
-optimizer: adamw_bnb_8bit
-lr_scheduler: cosine
-learning_rate: 0.0002
-
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 1
-xformers_attention:
-flash_attention: true
-
-warmup_steps: 10
-eval_steps: 20
-save_steps: 50
-debug:
-deepspeed:
-weight_decay: 0.0
-fsdp:
-fsdp_config:
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "</s>"
-  unk_token: "<unk>"
--- a/examples/mpt-7b/config.yml
+++ b/examples/mpt-7b/config.yml
@@ -20,7 +20,6 @@ lora_target_modules:
  - v_proj
 lora_fan_in_fan_out: false
 wandb_project: mpt-alpaca-7b
-wandb_entity:
 wandb_watch:
 wandb_run_id:
 wandb_log_model:
--- a/examples/openllama-3b/config.yml
+++ b/examples/openllama-3b/config.yml
@@ -22,7 +22,6 @@ lora_target_modules:
 lora_target_linear:
 lora_fan_in_fan_out:
 wandb_project:
-wandb_entity:
 wandb_watch:
 wandb_run_id:
 wandb_log_model:
--- a/examples/openllama-3b/lora.yml
+++ b/examples/openllama-3b/lora.yml
@@ -28,7 +28,6 @@ lora_target_modules:
  - o_proj
 lora_fan_in_fan_out:
 wandb_project:
-wandb_entity:
 wandb_watch:
 wandb_run_id:
 wandb_log_model:
--- a/examples/openllama-3b/qlora.yml
+++ b/examples/openllama-3b/qlora.yml
@@ -22,7 +22,6 @@ lora_target_modules:
 lora_target_linear: true
 lora_fan_in_fan_out:
 wandb_project:
-wandb_entity:
 wandb_watch:
 wandb_run_id:
 wandb_log_model:
@@ -35,7 +34,7 @@ torchdistx_path:
 lr_scheduler: cosine
 learning_rate: 0.0002
 train_on_inputs: false
-group_by_length: false
+group_by_length: true
 bf16: true
 fp16: false
 tf32: true
--- a/examples/pythia-12b/config.yml
+++ b/examples/pythia-12b/config.yml
@@ -23,7 +23,6 @@ lora_target_modules:
 lora_target_linear: true
 lora_fan_in_fan_out: true  # pythia/GPTNeoX lora specific
 wandb_project:
-wandb_entity:
 wandb_watch:
 wandb_run_id:
 wandb_log_model:
@@ -47,3 +46,4 @@ local_rank:
 gradient_checkpointing: true
 fsdp:
 fsdp_config:
+collator_pad_to_longest: true
--- a/examples/pythia/lora.yml
+++ b/examples/pythia/lora.yml
@@ -17,7 +17,6 @@ lora_target_modules:
 lora_target_linear:
 lora_fan_in_fan_out: true  # pythia/GPTNeoX lora specific
 wandb_project:
-wandb_entity:
 wandb_watch:
 wandb_run_id:
 wandb_log_model:
--- a/examples/redpajama/config-3b.yml
+++ b/examples/redpajama/config-3b.yml
@@ -21,7 +21,6 @@ lora_target_modules:
  - v_proj
 lora_fan_in_fan_out: false
 wandb_project: redpajama-alpaca-3b
-wandb_entity:
 wandb_watch:
 wandb_run_id:
 wandb_log_model:
--- a/examples/replit-3b/config-lora.yml
+++ b/examples/replit-3b/config-lora.yml
@@ -20,7 +20,6 @@ lora_target_modules:
  - mlp_down
 lora_fan_in_fan_out:
 wandb_project: lora-replit
-wandb_entity:
 wandb_watch:
 wandb_run_id:
 wandb_log_model:
--- a/examples/xgen-7b/xgen-7b-8k-qlora.yml
+++ b/examples/xgen-7b/xgen-7b-8k-qlora.yml
@@ -1,91 +0,0 @@
-# An example finetuning Saleforce's XGen-7b model with 8k context using qlora
-# on Tim Dettmer's Guanaco dataset.
-base_model: Salesforce/xgen-7b-8k-base
-base_model_config: Salesforce/xgen-7b-8k-base
-trust_remote_code: true
-model_type: AutoModelForCausalLM
-tokenizer_type: AutoTokenizer
-load_in_8bit: false
-# enable 4bit for QLoRA
-load_in_4bit: true
-gptq: false
-strict: false
-push_dataset_to_hub:
-datasets:
-  - path: timdettmers/openassistant-guanaco
-    data_files:
-      - openassistant_best_replies_train.jsonl
-    type: "completion"
-dataset_prepared_path: last_run_prepared
-val_set_size: 0.01
-# enable QLoRA
-adapter: qlora
-lora_model_dir:
-sequence_len: 8192
-max_packed_sequence_len:
-
-# hyperparameters from QLoRA paper Appendix B.2
-# "We find hyperparameters to be largely robust across datasets"
-lora_r: 64
-lora_alpha: 16
-# 0.1 for models up to 13B
-# 0.05 for 33B and 65B models
-lora_dropout: 0.05
-# add LoRA modules on all linear layers of the base model
-lora_target_modules:
-lora_target_linear: true
-lora_fan_in_fan_out:
-
-wandb_project:
-wandb_entity:
-wandb_watch:
-wandb_run_id:
-wandb_log_model:
-output_dir: ./qlora-out
-
-# QLoRA paper Table 9
-# - 16 for 7b & 13b
-# - 32 for 33b, 64 for 64b
-# Max size tested on A6000
-# - 7b: 40
-# - 40b: 4
-# decrease if OOM, increase for max VRAM utilization
-micro_batch_size: 1
-gradient_accumulation_steps: 1
-num_epochs: 3
-# Optimizer for QLoRA
-optimizer: paged_adamw_32bit
-torchdistx_path:
-lr_scheduler: cosine
-# QLoRA paper Table 9
-# - 2e-4 for 7b & 13b
-# - 1e-4 for 33b & 64b
-learning_rate: 0.00002
-train_on_inputs: false
-group_by_length: false
-bf16: true
-fp16: false
-tf32: false
-gradient_checkpointing: true
-# stop training after this many evaluation losses have increased in a row
-# https://huggingface.co/transformers/v4.2.2/_modules/transformers/trainer_callback.html#EarlyStoppingCallback
-early_stopping_patience: 3
-resume_from_checkpoint:
-auto_resume_from_checkpoints: true
-local_rank:
-logging_steps: 1
-xformers_attention: true
-flash_attention:
-gptq_groupsize:
-gptq_model_v1:
-warmup_steps: 10
-eval_steps: 50
-save_steps: 50
-debug:
-deepspeed:
-weight_decay: 0.0
-special_tokens:
-  eos_token: "<|endoftext|>"
-  bos_token: "<|endoftext|>"
-  unk_token: "<|endoftext|>"
-  pad_token: "<|endoftext|>"
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,28 +1,20 @@
-packaging
 peft @ git+https://github.com/huggingface/peft.git
 transformers @ git+https://github.com/huggingface/transformers.git
-bitsandbytes>=0.41.1
-accelerate @ git+https://github.com/huggingface/accelerate@2a289f6108e77a77a4efffb3f6316bc98538413b
+bitsandbytes>=0.39.0
+accelerate
 addict
-evaluate
 fire
-PyYAML>=6.0
+PyYAML==6.0
 datasets
-flash-attn>=2.0.8
+accelerate>=0.19.0
 sentencepiece
 wandb
 einops
 xformers
 optimum
-hf_transfer
-colorama
-numba
-numpy>=1.24.4
 # qlora things
 bert-score==0.3.13
 evaluate==0.4.0
 rouge-score==0.1.2
 scipy
 scikit-learn==1.2.2
-pynvml
-art
--- a/scripts/alpaca_json_to_jsonl.py
+++ b/scripts/alpaca_json_to_jsonl.py
@@ -0,0 +1,49 @@
+"""Module to convert json file to jsonl"""
+
+import os
+import sys
+from pathlib import Path
+from typing import Optional, Union
+
+import fire
+
+from axolotl.convert import (
+    FileReader,
+    FileWriter,
+    JsonlSerializer,
+    JsonParser,
+    JsonToJsonlConverter,
+    StdoutWriter,
+)
+
+# add src to the pythonpath so we don't need to pip install this
+project_root = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
+src_dir = os.path.join(project_root, "src")
+sys.path.insert(0, src_dir)
+
+
+def main(
+    file: Path,
+    output: Optional[Path] = None,
+    to_stdout: Optional[bool] = False,
+):
+    """
+    Convert a json file to jsonl
+    """
+
+    file_reader = FileReader()
+    writer: Union[StdoutWriter, FileWriter]
+    if to_stdout or output is None:
+        writer = StdoutWriter()
+    else:
+        writer = FileWriter(output)
+    json_parser = JsonParser()
+    jsonl_serializer = JsonlSerializer()
+
+    converter = JsonToJsonlConverter(file_reader, writer, json_parser, jsonl_serializer)
+
+    converter.convert(file, output)
+
+
+if __name__ == "__main__":
+    fire.Fire(main)
--- a/scripts/finetune.py
+++ b/scripts/finetune.py
@@ -4,49 +4,55 @@ import importlib
 import logging
 import os
 import random
+import signal
 import sys
 from pathlib import Path
 from typing import Any, Dict, List, Optional, Union

 import fire
 import torch
-import transformers
 import yaml

 # add src to the pythonpath so we don't need to pip install this
-from art import text2art
+from optimum.bettertransformer import BetterTransformer
 from transformers import GenerationConfig, TextStreamer

-from axolotl.common.cli import TrainerCliArgs, load_model_and_tokenizer
-from axolotl.logging_config import configure_logging
-from axolotl.train import TrainDatasetMeta, train
-from axolotl.utils.config import normalize_config, validate_config
-from axolotl.utils.data import prepare_dataset
+from axolotl.utils.data import load_prepare_datasets, load_pretraining_dataset
 from axolotl.utils.dict import DictDefault
-from axolotl.utils.distributed import is_main_process
-from axolotl.utils.models import load_model_config, load_tokenizer
+from axolotl.utils.models import load_model, load_tokenizer
 from axolotl.utils.tokenization import check_dataset_labels
+from axolotl.utils.trainer import setup_trainer
+from axolotl.utils.validation import validate_config
 from axolotl.utils.wandb import setup_wandb_env_vars

 project_root = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
 src_dir = os.path.join(project_root, "src")
 sys.path.insert(0, src_dir)

-configure_logging()
-LOG = logging.getLogger("axolotl.scripts")

-os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "1"
+logging.basicConfig(level=os.getenv("LOG_LEVEL", "INFO"))
+DEFAULT_DATASET_PREPARED_PATH = "last_run_prepared"


-def print_axolotl_text_art(suffix=None):
-    font = "nancyj"
-    ascii_text = "  axolotl"
-    if suffix:
-        ascii_text += f"  x  {suffix}"
-    ascii_art = text2art(" axolotl", font=font)
+def choose_device(cfg):
+    def get_device():
+        try:
+            if torch.cuda.is_available():
+                return f"cuda:{cfg.local_rank}"

-    if is_main_process():
-        print(ascii_art)
+            if torch.backends.mps.is_available():
+                return "mps"
+
+            raise SystemError("No CUDA/mps device found")
+        except Exception:  # pylint: disable=broad-exception-caught
+            return "cpu"
+
+    cfg.device = get_device()
+    if cfg.device_map != "auto":
+        if cfg.device.startswith("cuda"):
+            cfg.device_map = {"": cfg.local_rank}
+        else:
+            cfg.device_map = {"": cfg.device}


 def get_multi_line_input() -> Optional[str]:
@@ -58,45 +64,7 @@ def get_multi_line_input() -> Optional[str]:
    return instruction


-def do_merge_lora(
-    *,
-    cfg: DictDefault,
-    cli_args: TrainerCliArgs,
-):
-    model, tokenizer = load_model_and_tokenizer(cfg=cfg, cli_args=cli_args)
-    safe_serialization = cfg.save_safetensors is True
-
-    LOG.info("running merge of LoRA with base model")
-    model = model.merge_and_unload()
-    model.to(dtype=torch.float16)
-
-    if cfg.local_rank == 0:
-        LOG.info("saving merged model")
-        model.save_pretrained(
-            str(Path(cfg.output_dir) / "merged"),
-            safe_serialization=safe_serialization,
-        )
-        tokenizer.save_pretrained(str(Path(cfg.output_dir) / "merged"))
-
-
-def shard(
-    *,
-    cfg: DictDefault,
-    cli_args: TrainerCliArgs,
-):
-    model, _ = load_model_and_tokenizer(cfg=cfg, cli_args=cli_args)
-    safe_serialization = cfg.save_safetensors is True
-    LOG.debug("Re-saving model w/ sharding")
-    model.save_pretrained(cfg.output_dir, safe_serialization=safe_serialization)
-
-
-def do_inference(
-    *,
-    cfg: DictDefault,
-    cli_args: TrainerCliArgs,
-):
-    model, tokenizer = load_model_and_tokenizer(cfg=cfg, cli_args=cli_args)
-    prompter = cli_args.prompter
+def do_inference(cfg, model, tokenizer, prompter: Optional[str]):
    default_tokens = {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>"}

    for token, symbol in default_tokens.items():
@@ -118,8 +86,6 @@ def do_inference(
            max_seq_len=255, mem_freq=50, top_k=5, max_cache_size=None
        )

-    model = model.to(cfg.device)
-
    while True:
        print("=" * 80)
        # support for multiline inputs
@@ -171,10 +137,6 @@ def choose_config(path: Path):
            "No YAML config files found in the specified directory. Are you using a .yml extension?"
        )

-    if len(yaml_files) == 1:
-        print(f"Using default YAML file '{yaml_files[0]}'")
-        return yaml_files[0]
-
    print("Choose a YAML file:")
    for idx, file in enumerate(yaml_files):
        print(f"{idx + 1}. {file}")
@@ -197,7 +159,11 @@ def check_not_in(list1: List[str], list2: Union[Dict[str, Any], List[str]]) -> b
    return not any(el in list2 for el in list1)


-def load_cfg(config: Path = Path("examples/"), **kwargs):
+def train(
+    config: Path = Path("configs/"),
+    prepare_ds_only: bool = False,
+    **kwargs,
+):
    if Path(config).is_dir():
        config = choose_config(config)

@@ -216,72 +182,171 @@ def load_cfg(config: Path = Path("examples/"), **kwargs):
            else:
                cfg[k] = kwargs[k]

-    model_config = load_model_config(cfg)
-
-    # figure out if the model is llama
-    cfg.is_llama_derived_model = (
-        (hasattr(model_config, "model_type") and model_config.model_type == "llama")
-        or cfg.is_llama_derived_model
-        or "llama" in cfg.base_model
-        or (cfg.model_type and "llama" in cfg.model_type.lower())
-    )
    validate_config(cfg)

-    normalize_config(cfg)
+    # setup some derived config / hyperparams
+    cfg.gradient_accumulation_steps = cfg.gradient_accumulation_steps or (
+        cfg.batch_size // cfg.micro_batch_size
+    )
+    cfg.batch_size = (
+        cfg.batch_size or cfg.micro_batch_size * cfg.gradient_accumulation_steps
+    )
+    cfg.world_size = int(os.environ.get("WORLD_SIZE", 1))
+    cfg.local_rank = int(os.environ.get("LOCAL_RANK", 0))
+    choose_device(cfg)
+    cfg.ddp = cfg.ddp if cfg.ddp is not None else cfg.world_size != 1
+    if cfg.ddp:
+        cfg.device_map = {"": int(os.environ.get("LOCAL_RANK", 0))}
+        cfg.batch_size = cfg.batch_size * cfg.world_size

    setup_wandb_env_vars(cfg)
-    return cfg
+    if cfg.device == "mps":
+        cfg.load_in_8bit = False
+        cfg.tf32 = False
+        if cfg.bf16:
+            cfg.fp16 = True
+        cfg.bf16 = False

+    if cfg.tf32:
+        torch.backends.cuda.matmul.allow_tf32 = True

-def load_datasets(
-    *,
-    cfg: DictDefault,
-    cli_args: TrainerCliArgs,
-) -> TrainDatasetMeta:
-    tokenizer = load_tokenizer(cfg)
+    # load the tokenizer first
+    tokenizer_config = cfg.tokenizer_config or cfg.base_model_config
+    logging.info(f"loading tokenizer... {tokenizer_config}")
+    tokenizer = load_tokenizer(tokenizer_config, cfg.tokenizer_type, cfg)

-    train_dataset, eval_dataset, total_num_steps = prepare_dataset(cfg, tokenizer)
+    if (
+        check_not_in(["shard", "merge_lora"], kwargs) and not cfg.inference
+    ):  # don't need to load dataset for these
+        if not cfg.pretraining_dataset:
+            train_dataset, eval_dataset = load_prepare_datasets(
+                tokenizer, cfg, DEFAULT_DATASET_PREPARED_PATH
+            )
+        else:
+            train_dataset = load_pretraining_dataset(
+                cfg.pretraining_dataset,
+                tokenizer,
+                max_tokens=cfg.sequence_len,
+                seed=cfg.seed,
+            )
+            # https://discuss.huggingface.co/t/how-to-use-huggingface-trainer-streaming-datasets-without-wrapping-it-with-torchdatas-iterablewrapper/25230
+            train_dataset = train_dataset.with_format("torch")
+            eval_dataset = None

-    if cli_args.debug or cfg.debug:
-        LOG.info("check_dataset_labels...")
+    if cfg.debug or "debug" in kwargs:
+        logging.info("check_dataset_labels...")
        check_dataset_labels(
            train_dataset.select(
-                [
-                    random.randrange(0, len(train_dataset) - 1)  # nosec
-                    for _ in range(cli_args.debug_num_examples)
-                ]
+                [random.randrange(0, len(train_dataset) - 1) for _ in range(5)]  # nosec
            ),
            tokenizer,
-            num_examples=cli_args.debug_num_examples,
-            text_only=cli_args.debug_text_only,
        )

-    return TrainDatasetMeta(
-        train_dataset=train_dataset,
-        eval_dataset=eval_dataset,
-        total_num_steps=total_num_steps,
+    if prepare_ds_only:
+        logging.info("Finished preparing dataset. Exiting...")
+        return
+
+    # Load the model and tokenizer
+    logging.info("loading model and peft_config...")
+    model, peft_config = load_model(
+        cfg.base_model,
+        cfg.base_model_config,
+        cfg.model_type,
+        tokenizer,
+        cfg,
+        adapter=cfg.adapter,
    )

+    if "merge_lora" in kwargs and cfg.adapter is not None:
+        logging.info("running merge of LoRA with base model")
+        model = model.merge_and_unload()
+        model.to(dtype=torch.float16)

-def do_cli(config: Path = Path("examples/"), **kwargs):
-    print_axolotl_text_art()
-    parsed_cfg = load_cfg(config, **kwargs)
-    parser = transformers.HfArgumentParser((TrainerCliArgs))
-    parsed_cli_args, _ = parser.parse_args_into_dataclasses(
-        return_remaining_strings=True
-    )
-    if parsed_cli_args.inference:
-        do_inference(cfg=parsed_cfg, cli_args=parsed_cli_args)
-    elif parsed_cli_args.merge_lora:
-        do_merge_lora(cfg=parsed_cfg, cli_args=parsed_cli_args)
-    elif parsed_cli_args.shard:
-        shard(cfg=parsed_cfg, cli_args=parsed_cli_args)
+        if cfg.local_rank == 0:
+            logging.info("saving merged model")
+            model.save_pretrained(str(Path(cfg.output_dir) / "merged"))
+        return
+
+    if cfg.inference:
+        logging.info("calling do_inference function")
+        prompter: Optional[str] = "AlpacaPrompter"
+        if "prompter" in kwargs:
+            if kwargs["prompter"] == "None":
+                prompter = None
+            else:
+                prompter = kwargs["prompter"]
+        do_inference(cfg, model, tokenizer, prompter=prompter)
+        return
+
+    if "shard" in kwargs:
+        model.save_pretrained(cfg.output_dir)
+        return
+
+    trainer = setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer)
+
+    model.config.use_cache = False
+
+    if torch.__version__ >= "2" and sys.platform != "win32":
+        logging.info("Compiling torch model")
+        model = torch.compile(model)
+
+    # go ahead and presave, so we have the adapter config available to inspect
+    if peft_config:
+        logging.info(f"Pre-saving adapter config to {cfg.output_dir}")
+        peft_config.save_pretrained(cfg.output_dir)
+
+    # In case we want to stop early with ctrl+c, this is a nice to have to save the pretrained model
+    if cfg.local_rank == 0:
+
+        def terminate_handler(_, __, model):
+            if cfg.flash_optimum:
+                model = BetterTransformer.reverse(model)
+            model.save_pretrained(cfg.output_dir)
+            sys.exit(0)
+
+        signal.signal(
+            signal.SIGINT, lambda signum, frame: terminate_handler(signum, frame, model)
+        )
+
+    logging.info("Starting trainer...")
+    if cfg.group_by_length:
+        logging.info("hang tight... sorting dataset for group_by_length")
+    resume_from_checkpoint = cfg.resume_from_checkpoint
+    if cfg.resume_from_checkpoint is None and cfg.auto_resume_from_checkpoints:
+        possible_checkpoints = [
+            str(cp) for cp in Path(cfg.output_dir).glob("checkpoint-*")
+        ]
+        if len(possible_checkpoints) > 0:
+            sorted_paths = sorted(
+                possible_checkpoints,
+                key=lambda path: int(path.split("-")[-1]),
+            )
+            resume_from_checkpoint = sorted_paths[-1]
+            logging.info(
+                f"Using Auto-resume functionality to start with checkpoint at {resume_from_checkpoint}"
+            )
+
+    if not Path(cfg.output_dir).is_dir():
+        os.makedirs(cfg.output_dir, exist_ok=True)
+    if cfg.flash_optimum:
+        with torch.backends.cuda.sdp_kernel(
+            enable_flash=True, enable_math=True, enable_mem_efficient=True
+        ):
+            trainer.train(resume_from_checkpoint=resume_from_checkpoint)
    else:
-        dataset_meta = load_datasets(cfg=parsed_cfg, cli_args=parsed_cli_args)
-        if parsed_cli_args.prepare_ds_only:
-            return
-        train(cfg=parsed_cfg, cli_args=parsed_cli_args, dataset_meta=dataset_meta)
+        trainer.train(resume_from_checkpoint=resume_from_checkpoint)
+
+    logging.info(f"Training Completed!!! Saving pre-trained model to {cfg.output_dir}")
+
+    # TODO do we need this fix? https://huggingface.co/docs/accelerate/usage_guides/fsdp#saving-and-loading
+    # only save on rank 0, otherwise it corrupts output on multi-GPU when multiple processes attempt to write the same file
+    if cfg.local_rank == 0:
+        if cfg.flash_optimum:
+            model = BetterTransformer.reverse(model)
+        model.save_pretrained(cfg.output_dir)
+
+    # trainer.save_model(cfg.output_dir)  # TODO this may be needed for deepspeed to work? need to review another time


 if __name__ == "__main__":
-    fire.Fire(do_cli)
+    fire.Fire(train)
--- a/scripts/runpod-entrypoint.sh
+++ b/scripts/runpod-entrypoint.sh
@@ -1,21 +1,10 @@
 #!/bin/bash

-# Export specific ENV variables to /etc/rp_environment
-echo "Exporting environment variables..."
-printenv | grep -E '^RUNPOD_|^PATH=|^_=' | sed 's/^\(.*\)=\(.*\)$/export \1="\2"/' >> /etc/rp_environment
-echo 'source /etc/rp_environment' >> ~/.bashrc
+echo $PUBLIC_KEY >> ~/.ssh/authorized_keys
+chmod 700 -R ~/.ssh

-if [[ $PUBLIC_KEY ]]
-then
-    mkdir -p ~/.ssh
-    chmod 700 ~/.ssh
-    echo $PUBLIC_KEY >> ~/.ssh/authorized_keys
-    chmod 700 -R ~/.ssh
-    # Start the SSH service in the background
-    service ssh start
-else
-    echo "No PUBLIC_KEY ENV variable provided, not starting openSSH daemon"
-fi
+# Start the SSH service in the background
+service ssh start

 # Execute the passed arguments (CMD)
 exec "$@"
--- a/setup.py
+++ b/setup.py
@@ -7,7 +7,6 @@ with open("./requirements.txt", encoding="utf-8") as requirements_file:
    # don't include peft yet until we check the int4
    # need to manually install peft for now...
    reqs = [r.strip() for r in requirements_file.readlines() if "peft" not in r]
-    reqs = [r for r in reqs if "flash-attn" not in r]
    reqs = [r for r in reqs if r and r[0] != "#"]
    for r in reqs:
        install_requires.append(r)
@@ -26,14 +25,9 @@ setup(
        "gptq_triton": [
            "alpaca_lora_4bit[triton] @ git+https://github.com/winglian/alpaca_lora_4bit.git@setup_pip",
        ],
-        "flash-attn": [
-            "flash-attn==2.0.8",
-        ],
        "extras": [
+            "flash-attn",
            "deepspeed",
        ],
-        "peft": [
-            "peft @ git+https://github.com/huggingface/peft.git",
-        ],
    },
 )
--- a/src/axolotl/common/init.py
+++ b/src/axolotl/common/init.py
--- a/src/axolotl/common/cli.py
+++ b/src/axolotl/common/cli.py
@@ -1,43 +0,0 @@
-"""
-shared module for cli specific things
-"""
-
-import logging
-from dataclasses import dataclass, field
-from typing import Optional
-
-from axolotl.logging_config import configure_logging
-from axolotl.utils.dict import DictDefault
-from axolotl.utils.models import load_model, load_tokenizer
-
-configure_logging()
-LOG = logging.getLogger("axolotl.common.cli")
-
-
-@dataclass
-class TrainerCliArgs:
-    """
-    dataclass representing the various non-training arguments
-    """
-
-    debug: bool = field(default=False)
-    debug_text_only: bool = field(default=False)
-    debug_num_examples: int = field(default=5)
-    inference: bool = field(default=False)
-    merge_lora: bool = field(default=False)
-    prepare_ds_only: bool = field(default=False)
-    prompter: Optional[str] = field(default=None)
-    shard: bool = field(default=False)
-
-
-def load_model_and_tokenizer(
-    *,
-    cfg: DictDefault,
-    cli_args: TrainerCliArgs,
-):
-    LOG.info(f"loading tokenizer... {cfg.tokenizer_config or cfg.base_model_config}")
-    tokenizer = load_tokenizer(cfg)
-    LOG.info("loading model and (optionally) peft_config...")
-    model, _ = load_model(cfg, tokenizer, inference=cli_args.inference)
-
-    return model, tokenizer
--- a/src/axolotl/datasets.py
+++ b/src/axolotl/datasets.py
@@ -1,13 +1,12 @@
 """Module containing Dataset functionality"""

 import logging
-import os
 from typing import List

 import torch
-from datasets import Dataset, IterableDataset
+from datasets import IterableDataset

-from .prompt_tokenizers import PromptTokenizingStrategy
+from .prompt_tokenizers import InvalidDataException, PromptTokenizingStrategy

 # We want this to be a wrapper for an existing dataset that we have loaded
 # lets use the concept of middlewares to wrap each dataset, for example
@@ -15,12 +14,10 @@ from .prompt_tokenizers import PromptTokenizingStrategy
 # let's check to ensure we don't truncate an item in the middle, we'll use
 # the collators later on to pad the datasets

-LOG = logging.getLogger("axolotl")

-
-class TokenizedPromptDataset(Dataset):
+class TokenizedPromptDataset(IterableDataset):
    """
-    Dataset that returns tokenized prompts from a stream of text files.
+    Iterable dataset that returns tokenized prompts from a stream of text files.
        Args:
            prompt_tokenizer (PromptTokenizingStrategy): The prompt tokenizing method for proccessing the data.
            dataset (dataset.Dataset): Dataset with text files.
@@ -30,19 +27,22 @@ class TokenizedPromptDataset(Dataset):
        self,
        prompt_tokenizer: PromptTokenizingStrategy,
        dataset: IterableDataset,
-        **kwargs,
    ):
        self.prompt_tokenizer = prompt_tokenizer
-        super().__init__(self.process(dataset).data, **kwargs)
+        self.dataset = dataset

-    def process(self, dataset):
-        features = dataset.features.keys()
-        num_proc = min(64, os.cpu_count())
-        return dataset.map(
-            self.prompt_tokenizer.tokenize_prompt,
-            num_proc=num_proc,
-            remove_columns=features,
-        )
+    def __iter__(self):
+        iterator = iter(self.dataset)
+        count = 0
+        # Loop through the entire dataset
+        for example in iterator:
+            try:
+                yield self.prompt_tokenizer.tokenize_prompt(example)
+                count += 1
+            except InvalidDataException:
+                pass
+        if count == 0:
+            raise RuntimeError("Expected at least one datapoint in dataset.")


 # TODO this isn't the best since it can't interleave datasets
@@ -76,12 +76,7 @@ class ConstantLengthDataset(IterableDataset):
            self.tokens_dtype = torch.int64

    def __iter__(self):
-        buffer = {
-            "input_ids": [],
-            "attention_mask": [],
-            "labels": [],
-            "position_ids": [],
-        }
+        buffer = {"input_ids": [], "attention_mask": [], "labels": []}
        buffer_len = 0
        for dataset in self.datasets:
            idx = 0
@@ -112,9 +107,6 @@ class ConstantLengthDataset(IterableDataset):
                        attention_mask = torch.cat(buffer["attention_mask"], dim=-1)[
                            : self.seq_length
                        ]
-                        position_ids = torch.cat(buffer["position_ids"], dim=-1)[
-                            : self.seq_length
-                        ]
                        labels = torch.cat(buffer["labels"], dim=-1)[: self.seq_length]
                        if labels.size() == input_ids.size() and (
                            attention_mask.size() == input_ids.size()
@@ -123,17 +115,15 @@ class ConstantLengthDataset(IterableDataset):
                                "input_ids": input_ids,
                                "labels": labels,
                                "attention_mask": attention_mask,
-                                "position_ids": position_ids,
                            }
                        else:
-                            LOG.warning(
+                            logging.warning(
                                f"dropping batch due to tensor size mismatch input_ids: {input_ids.size()}, labels: {labels.size()}, attention_mask: {attention_mask.size()}"
                            )
                    buffer = {
                        "input_ids": [],
                        "attention_mask": [],
                        "labels": [],
-                        "position_ids": [],
                    }
                    buffer_len = 0
                    idx = 1
@@ -160,12 +150,8 @@ class ConstantLengthDataset(IterableDataset):
                        labels_with_concat = torch.tensor(
                            labels, dtype=self.tokens_dtype
                        )
-                        position_ids = torch.arange(
-                            len(input_ids), dtype=self.tokens_dtype
-                        )

                        buffer["input_ids"].append(input_ids_with_concat)
                        buffer["attention_mask"].append(attention_mask_with_concat)
                        buffer["labels"].append(labels_with_concat)
-                        buffer["position_ids"].append(position_ids)
                        buffer_len += len(input_ids)
--- a/src/axolotl/flash_attn.py
+++ b/src/axolotl/flash_attn.py
@@ -0,0 +1,140 @@
+"""Flash attention monkey patch for llama model"""
+
+# copied from https://github.com/lm-sys/FastChat/blob/main/fastchat/train/llama_flash_attn_monkey_patch.py
+
+from typing import Optional, Tuple
+
+import torch
+import transformers
+from einops import rearrange
+from flash_attn.bert_padding import pad_input, unpad_input
+from flash_attn.flash_attn_interface import flash_attn_unpadded_qkvpacked_func
+from transformers.models.llama.modeling_llama import apply_rotary_pos_emb
+
+
+def forward(
+    self,
+    hidden_states: torch.Tensor,
+    attention_mask: Optional[torch.Tensor] = None,
+    position_ids: Optional[torch.Tensor] = None,
+    past_key_value: Optional[Tuple[torch.Tensor]] = None,
+    output_attentions: bool = False,
+    use_cache: bool = False,
+) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]:
+    """Input shape: Batch x Time x Channel
+
+    attention_mask: [bsz, q_len]
+    """
+    # pylint: disable=duplicate-code
+    bsz, q_len, _ = hidden_states.size()
+
+    query_states = (
+        self.q_proj(hidden_states)
+        .view(bsz, q_len, self.num_heads, self.head_dim)
+        .transpose(1, 2)
+    )
+    key_states = (
+        self.k_proj(hidden_states)
+        .view(bsz, q_len, self.num_heads, self.head_dim)
+        .transpose(1, 2)
+    )
+    value_states = (
+        self.v_proj(hidden_states)
+        .view(bsz, q_len, self.num_heads, self.head_dim)
+        .transpose(1, 2)
+    )
+    # [bsz, q_len, nh, hd]
+    # [bsz, nh, q_len, hd]
+
+    kv_seq_len = key_states.shape[-2]
+    assert past_key_value is None, "past_key_value is not supported"
+
+    cos, sin = self.rotary_emb(value_states, seq_len=kv_seq_len)
+    query_states, key_states = apply_rotary_pos_emb(
+        query_states, key_states, cos, sin, position_ids
+    )
+    # [bsz, nh, t, hd]
+    assert not output_attentions, "output_attentions is not supported"
+    assert not use_cache, "use_cache is not supported"
+
+    # Flash attention codes from
+    # https://github.com/HazyResearch/flash-attention/blob/main/flash_attn/flash_attention.py
+
+    # transform the data into the format required by flash attention
+    qkv = torch.stack(
+        [query_states, key_states, value_states], dim=2
+    )  # [bsz, nh, 3, q_len, hd]
+    qkv = qkv.transpose(1, 3)  # [bsz, q_len, 3, nh, hd]
+    # We have disabled _prepare_decoder_attention_mask in LlamaModel
+    # the attention_mask should be the same as the key_padding_mask
+    key_padding_mask = attention_mask
+
+    if key_padding_mask is None:
+        qkv = rearrange(qkv, "b s ... -> (b s) ...")
+        max_s = q_len
+        cu_q_lens = torch.arange(
+            0,
+            (bsz + 1) * q_len,
+            step=q_len,
+            dtype=torch.int32,
+            device=qkv.device,
+        )
+        output = flash_attn_unpadded_qkvpacked_func(
+            qkv, cu_q_lens, max_s, 0.0, softmax_scale=None, causal=True
+        )
+        output = rearrange(output, "(b s) ... -> b s ...", b=bsz)
+    else:
+        nheads = qkv.shape[-2]
+
+        # pylint: disable=invalid-name
+        x = rearrange(qkv, "b s three h d -> b s (three h d)")
+        x_unpad, indices, cu_q_lens, max_s = unpad_input(x, key_padding_mask)
+        x_unpad = rearrange(
+            x_unpad,
+            "nnz (three h d) -> nnz three h d",
+            three=3,
+            h=nheads,
+        )
+        output_unpad = flash_attn_unpadded_qkvpacked_func(
+            x_unpad,
+            cu_q_lens,
+            max_s,
+            0.0,
+            softmax_scale=None,
+            causal=True,
+        )
+        output = rearrange(
+            pad_input(
+                rearrange(output_unpad, "nnz h d -> nnz (h d)"),
+                indices,
+                bsz,
+                q_len,
+            ),
+            "b s (h d) -> b s h d",
+            h=nheads,
+        )
+    return (
+        self.o_proj(rearrange(output, "b s h d -> b s (h d)")),
+        None,
+        None,
+    )
+
+
+# Disable the transformation of the attention mask in LlamaModel as the flash attention
+# requires the attention mask to be the same as the key_padding_mask
+def _prepare_decoder_attention_mask(
+    self,
+    attention_mask,
+    input_shape,
+    inputs_embeds,
+    past_key_values_length,
+):  # pylint: disable=unused-argument
+    # [bsz, seq_len]
+    return attention_mask
+
+
+def replace_llama_attn_with_flash_attn():
+    transformers.models.llama.modeling_llama.LlamaModel._prepare_decoder_attention_mask = (  # pylint: disable=protected-access
+        _prepare_decoder_attention_mask
+    )
+    transformers.models.llama.modeling_llama.LlamaAttention.forward = forward
--- a/src/axolotl/logging_config.py
+++ b/src/axolotl/logging_config.py
@@ -1,70 +0,0 @@
-"""
-Common logging module for axolotl
-"""
-
-import os
-import sys
-from logging import Formatter
-from logging.config import dictConfig
-from typing import Any, Dict
-
-from colorama import Fore, Style, init
-
-
-class ColorfulFormatter(Formatter):
-    """
-    Formatter to add coloring to log messages by log type
-    """
-
-    COLORS = {
-        "WARNING": Fore.YELLOW,
-        "ERROR": Fore.RED,
-        "CRITICAL": Fore.RED + Style.BRIGHT,
-    }
-
-    def format(self, record):
-        log_message = super().format(record)
-        return self.COLORS.get(record.levelname, "") + log_message + Fore.RESET
-
-
-DEFAULT_LOGGING_CONFIG: Dict[str, Any] = {
-    "version": 1,
-    "formatters": {
-        "simple": {
-            "format": "[%(asctime)s] [%(levelname)s] [%(name)s.%(funcName)s:%(lineno)d] [PID:%(process)d] %(message)s",
-        },
-        "colorful": {
-            "()": ColorfulFormatter,
-            "format": "[%(asctime)s] [%(levelname)s] [%(name)s.%(funcName)s:%(lineno)d] [PID:%(process)d] %(message)s",
-        },
-    },
-    "filters": {},
-    "handlers": {
-        "console": {
-            "class": "logging.StreamHandler",
-            "formatter": "simple",
-            "filters": [],
-            "stream": sys.stdout,
-        },
-        "color_console": {
-            "class": "logging.StreamHandler",
-            "formatter": "colorful",
-            "filters": [],
-            "stream": sys.stdout,
-        },
-    },
-    "root": {"handlers": ["console"], "level": os.getenv("LOG_LEVEL", "INFO")},
-    "loggers": {
-        "axolotl": {
-            "handlers": ["color_console"],
-            "level": "DEBUG",
-            "propagate": False,
-        },
-    },
-}
-
-
-def configure_logging():
-    """Configure with default logging"""
-    init()  # Initialize colorama
-    dictConfig(DEFAULT_LOGGING_CONFIG)
--- a/src/axolotl/monkeypatch/llama_attn_hijack_flash.py
+++ b/src/axolotl/monkeypatch/llama_attn_hijack_flash.py
@@ -1,598 +0,0 @@
-"""Flash attention monkey patch for llama model"""
-
-# copied from https://github.com/lm-sys/FastChat/blob/main/fastchat/train/llama_flash_attn_monkey_patch.py
-
-import warnings
-from typing import List, Optional, Tuple, Union
-
-import torch
-import torch.nn.functional as F
-import transformers
-from einops import rearrange
-from flash_attn.bert_padding import pad_input, unpad_input
-from transformers.modeling_outputs import BaseModelOutputWithPast
-from transformers.models.llama.modeling_llama import (
-    LlamaDecoderLayer as OriginalLlamaDecoderLayer,
-)
-from transformers.models.llama.modeling_llama import apply_rotary_pos_emb, repeat_kv
-
-from axolotl.monkeypatch.utils import get_cu_seqlens_from_pos_ids
-
-try:
-    from flash_attn.flash_attn_interface import (  # pylint: disable=ungrouped-imports
-        flash_attn_kvpacked_func,
-        flash_attn_varlen_kvpacked_func,
-        flash_attn_varlen_qkvpacked_func,
-    )
-except ImportError:
-    from flash_attn.flash_attn_interface import (
-        flash_attn_unpadded_kvpacked_func as flash_attn_varlen_kvpacked_func,
-    )
-    from flash_attn.flash_attn_interface import (
-        flash_attn_unpadded_qkvpacked_func as flash_attn_varlen_qkvpacked_func,
-    )
-
-
-def replace_llama_attn_with_flash_attn(packed: Optional[bool] = False):
-    transformers.models.llama.modeling_llama.LlamaModel._prepare_decoder_attention_mask = (  # pylint: disable=protected-access
-        _prepare_decoder_attention_mask
-    )
-    transformers.models.llama.modeling_llama.LlamaAttention.forward = flashattn_forward
-    if packed:
-        transformers.models.llama.modeling_llama.LlamaDecoderLayer = LlamaDecoderLayer
-        transformers.models.llama.modeling_llama.LlamaModel.forward = (
-            llama_model_forward
-        )
-
-
-# Disable the transformation of the attention mask in LlamaModel as the flash attention
-# requires the attention mask to be the same as the key_padding_mask
-def _prepare_decoder_attention_mask(
-    self,
-    attention_mask,
-    input_shape,
-    inputs_embeds,
-    past_key_values_length,
-):  # pylint: disable=unused-argument
-    # [bsz, seq_len]
-    return attention_mask
-
-
-def flashattn_forward(
-    self,
-    hidden_states: torch.Tensor,
-    attention_mask: Optional[torch.Tensor] = None,
-    position_ids: Optional[torch.Tensor] = None,
-    past_key_value: Optional[Tuple[torch.Tensor]] = None,
-    output_attentions: bool = False,
-    use_cache: bool = False,
-    cu_seqlens: Optional[torch.Tensor] = None,
-    max_seqlen: Optional[torch.Tensor] = None,
-) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]:
-    """Input shape: Batch x Time x Channel
-
-    attention_mask: [bsz, q_len]
-    """
-    # pylint: disable=duplicate-code
-    bsz, q_len, _ = hidden_states.size()
-
-    if not hasattr(self, "pretraining_tp"):
-        self.pretraining_tp = 1
-
-    if self.pretraining_tp > 1:
-        key_value_slicing = (
-            self.num_key_value_heads * self.head_dim
-        ) // self.pretraining_tp
-        query_slices = self.q_proj.weight.split(
-            (self.num_heads * self.head_dim) // self.pretraining_tp, dim=0
-        )
-        key_slices = self.k_proj.weight.split(key_value_slicing, dim=0)
-        value_slices = self.v_proj.weight.split(key_value_slicing, dim=0)
-
-        query_states = [
-            F.linear(hidden_states, query_slices[i]) for i in range(self.pretraining_tp)
-        ]
-        query_states = torch.cat(query_states, dim=-1)
-
-        key_states = [
-            F.linear(hidden_states, key_slices[i]) for i in range(self.pretraining_tp)
-        ]
-        key_states = torch.cat(key_states, dim=-1)
-
-        value_states = [
-            F.linear(hidden_states, value_slices[i]) for i in range(self.pretraining_tp)
-        ]
-        value_states = torch.cat(value_states, dim=-1)
-
-    else:
-        query_states = self.q_proj(hidden_states)
-        key_states = self.k_proj(hidden_states)
-        value_states = self.v_proj(hidden_states)
-
-    query_states = query_states.view(
-        bsz, q_len, self.num_heads, self.head_dim
-    ).transpose(1, 2)
-    key_states = key_states.view(
-        bsz, q_len, self.num_key_value_heads, self.head_dim
-    ).transpose(1, 2)
-    value_states = value_states.view(
-        bsz, q_len, self.num_key_value_heads, self.head_dim
-    ).transpose(1, 2)
-    # [bsz, q_len, nh, hd]
-    # [bsz, nh, q_len, hd]
-
-    kv_seq_len = key_states.shape[-2]
-    if past_key_value is not None:
-        kv_seq_len += past_key_value[0].shape[-2]
-
-    cos, sin = self.rotary_emb(value_states, seq_len=kv_seq_len)
-    query_states, key_states = apply_rotary_pos_emb(
-        query_states, key_states, cos, sin, position_ids
-    )
-    # [bsz, nh, t, hd]
-
-    if past_key_value is not None:
-        # reuse k, v, self_attention
-        key_states = torch.cat([past_key_value[0], key_states], dim=2)
-        value_states = torch.cat([past_key_value[1], value_states], dim=2)
-
-    past_key_value = (key_states, value_states) if use_cache else None
-
-    # repeat k/v heads if n_kv_heads < n_heads
-    key_states = repeat_kv(key_states, self.num_key_value_groups)
-    value_states = repeat_kv(value_states, self.num_key_value_groups)
-
-    if output_attentions:
-        warnings.warn(
-            "Output attentions is not supported for patched `LlamaAttention`, returning `None` instead."
-        )
-
-    #
-    # flash-attn v2 start
-    #
-
-    if self.training:
-        # during training q,k,v always have same seqlen
-        assert key_states.shape == query_states.shape
-        is_causal = True
-    else:
-        # turn off FA causal mask after first inference autoregressive iteration
-        # only on first autoregressive step q,k,v have same seqlen
-        is_causal = key_states.shape == query_states.shape
-
-    if cu_seqlens is not None and max_seqlen is not None:
-        # special handling using sample packing
-        qkv = torch.stack(
-            [query_states, key_states, value_states], dim=2
-        )  # [bsz, nh, 3, q_len, hd]
-        qkv = qkv.transpose(1, 3)  # [bsz, q_len, 3, nh, hd]
-        qkv = rearrange(qkv, "b s ... -> (b s) ...")
-
-        output = flash_attn_varlen_qkvpacked_func(
-            qkv, cu_seqlens, max_seqlen, 0.0, softmax_scale=None, causal=True
-        )
-        output = rearrange(output, "(b s) ... -> b s ...", b=bsz)
-    elif query_states.shape == key_states.shape:
-        query_states = query_states.transpose(1, 2)
-        key_states = key_states.transpose(1, 2)
-        value_states = value_states.transpose(1, 2)
-        qkv_unpad, cu_seqlens_q, max_seqlen_q, _, output_pad_fn = generate_qkv(
-            query_states,
-            key_states,
-            value_states,
-            qkvpacked=True,
-            # We have disabled _prepare_decoder_attention_mask in LlamaModel
-            # the attention_mask should be the same as the key_padding_mask
-            key_padding_mask=attention_mask,
-            query_padding_mask=attention_mask[:, -query_states.size(1) :]
-            if attention_mask is not None
-            else None,
-        )
-        output_unpad = flash_attn_varlen_qkvpacked_func(
-            qkv_unpad,
-            cu_seqlens_q,
-            max_seqlen_q,
-            0.0,
-            softmax_scale=None,
-            causal=is_causal,
-        )
-        output = output_pad_fn(output_unpad)
-    else:
-        query_states = query_states.transpose(1, 2)
-        key_states = key_states.transpose(1, 2)
-        value_states = value_states.transpose(1, 2)
-        if attention_mask is None or attention_mask.all().item():
-            output = flash_attn_kvpacked_func(
-                query_states,
-                torch.stack([key_states, value_states], 2),
-                causal=is_causal,
-            )
-        else:
-            (  # pylint: disable=unbalanced-tuple-unpacking
-                q_unpad,
-                kv_unpad,
-                cu_seqlens_q,
-                cu_seqlens_k,
-                max_seqlen_q,
-                max_seqlen_k,
-                _,
-                _,
-                output_pad_fn,
-            ) = generate_qkv(
-                query_states,
-                key_states,
-                value_states,
-                kvpacked=True,
-                key_padding_mask=attention_mask,
-                query_padding_mask=attention_mask[:, -query_states.size(1) :]
-                if attention_mask is not None
-                else None,
-            )
-            output_unpad = flash_attn_varlen_kvpacked_func(
-                q_unpad,
-                kv_unpad,
-                cu_seqlens_q,
-                cu_seqlens_k,
-                max_seqlen_q,
-                max_seqlen_k,
-                0.0,
-                softmax_scale=None,
-                causal=is_causal,
-            )
-            output = output_pad_fn(output_unpad)
-
-    attn_output = output
-    if attn_output.size() != (bsz, q_len, self.num_heads, self.head_dim):
-        raise ValueError(
-            f"`attn_output` should be of size {(bsz, q_len, self.num_heads, self.head_dim)}, but is"
-            f" {attn_output.size()}"
-        )
-    attn_output = rearrange(attn_output, "b s h d -> b s (h d)")
-
-    #
-    # flash-attn v2 end
-    #
-
-    if self.pretraining_tp > 1:
-        attn_output = attn_output.split(self.hidden_size // self.pretraining_tp, dim=2)
-        o_proj_slices = self.o_proj.weight.split(
-            self.hidden_size // self.pretraining_tp, dim=1
-        )
-        attn_output = sum(
-            F.linear(attn_output[i], o_proj_slices[i])
-            for i in range(self.pretraining_tp)
-        )
-    else:
-        attn_output = self.o_proj(attn_output)
-
-    return attn_output, None, past_key_value
-
-
-# based on https://github.com/Dao-AILab/flash-attention/blob/364a5b/tests/test_flash_attn.py#L38
-def generate_qkv(
-    q,
-    k,
-    v,
-    query_padding_mask=None,
-    key_padding_mask=None,
-    kvpacked=False,
-    qkvpacked=False,
-):  # pylint: disable=invalid-name,unnecessary-lambda-assignment
-    """
-    Arguments:
-        q: (batch_size, seqlen_q, nheads, d)
-        k: (batch_size, seqlen_k, nheads_k, d)
-        v: (batch_size, seqlen_k, nheads_k, d)
-        query_padding_mask: (batch_size, seqlen), bool
-        key_padding_mask: (batch_size, seqlen), bool
-    """
-    assert not (kvpacked and qkvpacked)
-    batch_size, seqlen_q, nheads, d = q.shape
-    _, seqlen_k, nheads_k, _ = k.shape
-    assert k.shape == (batch_size, seqlen_k, nheads_k, d)
-    assert v.shape == (batch_size, seqlen_k, nheads_k, d)
-
-    if query_padding_mask is not None:
-        q_unpad, indices_q, cu_seqlens_q, max_seqlen_q = unpad_input(
-            q, query_padding_mask
-        )
-
-        output_pad_fn = lambda output_unpad: pad_input(  # noqa: E731
-            output_unpad, indices_q, batch_size, seqlen_q
-        )
-
-    else:
-        q_unpad = rearrange(q, "b s h d -> (b s) h d")
-        cu_seqlens_q = torch.arange(
-            0,
-            (batch_size + 1) * seqlen_q,
-            step=seqlen_q,
-            dtype=torch.int32,
-            device=q_unpad.device,
-        )
-        max_seqlen_q = seqlen_q
-
-        output_pad_fn = lambda output_unpad: rearrange(  # noqa: E731
-            output_unpad, "(b s) h d -> b s h d", b=batch_size
-        )
-
-    if key_padding_mask is not None:
-        k_unpad, _, cu_seqlens_k, max_seqlen_k = unpad_input(k, key_padding_mask)
-        v_unpad, _, _, _ = unpad_input(v, key_padding_mask)
-    else:
-        k_unpad = rearrange(k, "b s h d -> (b s) h d")
-        v_unpad = rearrange(v, "b s h d -> (b s) h d")
-        cu_seqlens_k = torch.arange(
-            0,
-            (batch_size + 1) * seqlen_k,
-            step=seqlen_k,
-            dtype=torch.int32,
-            device=k_unpad.device,
-        )
-        max_seqlen_k = seqlen_k
-
-    if qkvpacked:
-        assert nheads == nheads_k
-        qkv_unpad = torch.stack([q_unpad, k_unpad, v_unpad], dim=1)
-        qkv = torch.stack([q, k, v], dim=2)
-        return (qkv_unpad, cu_seqlens_q, max_seqlen_q, qkv, output_pad_fn)
-
-    if kvpacked:
-        kv_unpad = torch.stack([k_unpad, v_unpad], dim=1)
-        kv = torch.stack([k, v], dim=2)
-        return (
-            q_unpad,
-            kv_unpad,
-            cu_seqlens_q,
-            cu_seqlens_k,
-            max_seqlen_q,
-            max_seqlen_k,
-            q,
-            kv,
-            output_pad_fn,
-        )
-
-    return (
-        q_unpad,
-        k_unpad,
-        v_unpad,
-        cu_seqlens_q,
-        cu_seqlens_k,
-        max_seqlen_q,
-        max_seqlen_k,
-        q,
-        k,
-        v,
-        output_pad_fn,
-    )
-
-
-def llama_model_forward(
-    self,
-    input_ids: torch.LongTensor = None,
-    attention_mask: Optional[torch.Tensor] = None,
-    position_ids: Optional[torch.LongTensor] = None,
-    past_key_values: Optional[List[torch.FloatTensor]] = None,
-    inputs_embeds: Optional[torch.FloatTensor] = None,
-    use_cache: Optional[bool] = None,
-    output_attentions: Optional[bool] = None,
-    output_hidden_states: Optional[bool] = None,
-    return_dict: Optional[bool] = None,
-) -> Union[Tuple, BaseModelOutputWithPast]:
-    output_attentions = (
-        output_attentions
-        if output_attentions is not None
-        else self.config.output_attentions
-    )
-    output_hidden_states = (
-        output_hidden_states
-        if output_hidden_states is not None
-        else self.config.output_hidden_states
-    )
-    use_cache = use_cache if use_cache is not None else self.config.use_cache
-
-    return_dict = (
-        return_dict if return_dict is not None else self.config.use_return_dict
-    )
-
-    # retrieve input_ids and inputs_embeds
-    if input_ids is not None and inputs_embeds is not None:
-        raise ValueError(
-            "You cannot specify both decoder_input_ids and decoder_inputs_embeds at the same time"
-        )
-    if input_ids is not None:
-        batch_size, seq_length = input_ids.shape
-    elif inputs_embeds is not None:
-        batch_size, seq_length, _ = inputs_embeds.shape
-    else:
-        raise ValueError(
-            "You have to specify either decoder_input_ids or decoder_inputs_embeds"
-        )
-
-    seq_length_with_past = seq_length
-    past_key_values_length = 0
-
-    if past_key_values is not None:
-        past_key_values_length = past_key_values[0][0].shape[2]
-        seq_length_with_past = seq_length_with_past + past_key_values_length
-
-    cu_seqlens = None
-    max_seqlen = None
-    if position_ids is None:
-        device = input_ids.device if input_ids is not None else inputs_embeds.device
-        position_ids = torch.arange(
-            past_key_values_length,
-            seq_length + past_key_values_length,
-            dtype=torch.long,
-            device=device,
-        )
-        position_ids = position_ids.unsqueeze(0).view(-1, seq_length)
-    else:
-        position_ids = position_ids.view(-1, seq_length).long()
-        cu_seqlens, max_seqlen = get_cu_seqlens_from_pos_ids(position_ids)
-        cu_seqlens = cu_seqlens.squeeze()
-
-    if inputs_embeds is None:
-        inputs_embeds = self.embed_tokens(input_ids)
-    # embed positions
-    if attention_mask is None:
-        attention_mask = torch.ones(
-            (batch_size, seq_length_with_past),
-            dtype=torch.bool,
-            device=inputs_embeds.device,
-        )
-    attention_mask = (
-        self._prepare_decoder_attention_mask(  # pylint: disable=protected-access
-            attention_mask,
-            (batch_size, seq_length),
-            inputs_embeds,
-            past_key_values_length,
-        )
-    )
-
-    hidden_states = inputs_embeds
-
-    if self.gradient_checkpointing and self.training:
-        if use_cache:
-            transformers.logger.warning_once(
-                "`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`..."
-            )
-            use_cache = False
-
-    # decoder layers
-    all_hidden_states = () if output_hidden_states else None
-    all_self_attns = () if output_attentions else None
-    next_decoder_cache = () if use_cache else None
-
-    for idx, decoder_layer in enumerate(self.layers):
-        if output_hidden_states:
-            all_hidden_states += (hidden_states,)
-
-        past_key_value = past_key_values[idx] if past_key_values is not None else None
-
-        if self.gradient_checkpointing and self.training:
-
-            def create_custom_forward(module):
-                def custom_forward(*inputs):
-                    # None for past_key_value
-                    return module(*inputs)
-
-                return custom_forward
-
-            layer_outputs = torch.utils.checkpoint.checkpoint(
-                create_custom_forward(decoder_layer),
-                hidden_states,
-                attention_mask,
-                position_ids,
-                None,
-                output_attentions,
-                None,
-                cu_seqlens,
-                max_seqlen,
-            )
-        else:
-            layer_outputs = decoder_layer(
-                hidden_states,
-                attention_mask=attention_mask,
-                position_ids=position_ids,
-                past_key_value=past_key_value,
-                output_attentions=output_attentions,
-                use_cache=use_cache,
-                cu_seqlens=cu_seqlens,
-                max_seqlen=max_seqlen,
-            )
-
-        hidden_states = layer_outputs[0]
-
-        if use_cache:
-            next_decoder_cache += (layer_outputs[2 if output_attentions else 1],)
-
-        if output_attentions:
-            all_self_attns += (layer_outputs[1],)
-
-    hidden_states = self.norm(hidden_states)
-
-    # add hidden states from the last decoder layer
-    if output_hidden_states:
-        all_hidden_states += (hidden_states,)
-
-    next_cache = next_decoder_cache if use_cache else None
-    if not return_dict:
-        return tuple(
-            v
-            for v in [hidden_states, next_cache, all_hidden_states, all_self_attns]
-            if v is not None
-        )
-    return BaseModelOutputWithPast(
-        last_hidden_state=hidden_states,
-        past_key_values=next_cache,
-        hidden_states=all_hidden_states,
-        attentions=all_self_attns,
-    )
-
-
-class LlamaDecoderLayer(OriginalLlamaDecoderLayer):
-    """
-    patched version of LlamaDecoderLayer to pass through the precalculated cu_seqlens
-    """
-
-    def forward(
-        self,
-        hidden_states: torch.Tensor,
-        attention_mask: Optional[torch.Tensor] = None,
-        position_ids: Optional[torch.LongTensor] = None,
-        past_key_value: Optional[Tuple[torch.Tensor]] = None,
-        output_attentions: Optional[bool] = False,
-        use_cache: Optional[bool] = False,
-        cu_seqlens: Optional[torch.Tensor] = None,
-        max_seqlen: Optional[torch.Tensor] = None,
-    ) -> Tuple[
-        torch.FloatTensor, Optional[Tuple[torch.FloatTensor, torch.FloatTensor]]
-    ]:
-        """
-        Args:
-            hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)`
-            attention_mask (`torch.FloatTensor`, *optional*): attention mask of size
-                `(batch, 1, tgt_len, src_len)` where padding elements are indicated by very large negative values.
-            output_attentions (`bool`, *optional*):
-                Whether or not to return the attentions tensors of all attention layers. See `attentions` under
-                returned tensors for more detail.
-            use_cache (`bool`, *optional*):
-                If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding
-                (see `past_key_values`).
-            past_key_value (`Tuple(torch.FloatTensor)`, *optional*): cached past key and value projection states
-            cu_seqlens (`torch.Tensor`, *optional*) cumulative sequence len when packing
-        """
-
-        residual = hidden_states
-
-        hidden_states = self.input_layernorm(hidden_states)
-
-        # Self Attention
-        hidden_states, self_attn_weights, present_key_value = self.self_attn(
-            hidden_states=hidden_states,
-            attention_mask=attention_mask,
-            position_ids=position_ids,
-            past_key_value=past_key_value,
-            output_attentions=output_attentions,
-            use_cache=use_cache,
-            cu_seqlens=cu_seqlens,
-            max_seqlen=max_seqlen,
-        )
-        hidden_states = residual + hidden_states
-
-        # Fully Connected
-        residual = hidden_states
-        hidden_states = self.post_attention_layernorm(hidden_states)
-        hidden_states = self.mlp(hidden_states)
-        hidden_states = residual + hidden_states
-
-        outputs = (hidden_states,)
-
-        if output_attentions:
-            outputs += (self_attn_weights,)
-
-        if use_cache:
-            outputs += (present_key_value,)
-
-        return outputs
--- a/src/axolotl/monkeypatch/llama_attn_hijack_sdp.py
+++ b/src/axolotl/monkeypatch/llama_attn_hijack_sdp.py
@@ -1,140 +0,0 @@
-"""
-Patched LlamaAttention to use torch.nn.functional.scaled_dot_product_attention
-"""
-
-import warnings
-from typing import Optional, Tuple
-
-import torch
-import torch.nn.functional as F
-import transformers.models.llama.modeling_llama
-from transformers.models.llama.modeling_llama import apply_rotary_pos_emb, repeat_kv
-
-
-def hijack_llama_sdp_attention():
-    transformers.models.llama.modeling_llama.LlamaAttention.forward = (
-        sdp_attention_forward
-    )
-
-
-def sdp_attention_forward(
-    self,
-    hidden_states: torch.Tensor,
-    attention_mask: Optional[torch.Tensor] = None,
-    position_ids: Optional[torch.LongTensor] = None,
-    past_key_value: Optional[Tuple[torch.Tensor]] = None,
-    output_attentions: bool = False,
-    use_cache: bool = False,
-) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]:
-    # pylint: disable=duplicate-code
-    bsz, q_len, _ = hidden_states.size()
-
-    if not hasattr(self, "pretraining_tp"):
-        self.pretraining_tp = 1
-
-    if self.pretraining_tp > 1:
-        key_value_slicing = (
-            self.num_key_value_heads * self.head_dim
-        ) // self.pretraining_tp
-        query_slices = self.q_proj.weight.split(
-            (self.num_heads * self.head_dim) // self.pretraining_tp, dim=0
-        )
-        key_slices = self.k_proj.weight.split(key_value_slicing, dim=0)
-        value_slices = self.v_proj.weight.split(key_value_slicing, dim=0)
-
-        query_states = [
-            F.linear(hidden_states, query_slices[i]) for i in range(self.pretraining_tp)
-        ]
-        query_states = torch.cat(query_states, dim=-1)
-
-        key_states = [
-            F.linear(hidden_states, key_slices[i]) for i in range(self.pretraining_tp)
-        ]
-        key_states = torch.cat(key_states, dim=-1)
-
-        value_states = [
-            F.linear(hidden_states, value_slices[i]) for i in range(self.pretraining_tp)
-        ]
-        value_states = torch.cat(value_states, dim=-1)
-
-    else:
-        query_states = self.q_proj(hidden_states)
-        key_states = self.k_proj(hidden_states)
-        value_states = self.v_proj(hidden_states)
-
-    query_states = query_states.view(
-        bsz, q_len, self.num_heads, self.head_dim
-    ).transpose(1, 2)
-    key_states = key_states.view(
-        bsz, q_len, self.num_key_value_heads, self.head_dim
-    ).transpose(1, 2)
-    value_states = value_states.view(
-        bsz, q_len, self.num_key_value_heads, self.head_dim
-    ).transpose(1, 2)
-    # [bsz, q_len, nh, hd]
-    # [bsz, nh, q_len, hd]
-
-    kv_seq_len = key_states.shape[-2]
-    if past_key_value is not None:
-        kv_seq_len += past_key_value[0].shape[-2]
-
-    cos, sin = self.rotary_emb(value_states, seq_len=kv_seq_len)
-    query_states, key_states = apply_rotary_pos_emb(
-        query_states, key_states, cos, sin, position_ids
-    )
-    # [bsz, nh, t, hd]
-
-    if past_key_value is not None:
-        # reuse k, v, self_attention
-        key_states = torch.cat([past_key_value[0], key_states], dim=2)
-        value_states = torch.cat([past_key_value[1], value_states], dim=2)
-
-    past_key_value = (key_states, value_states) if use_cache else None
-
-    # repeat k/v heads if n_kv_heads < n_heads
-    key_states = repeat_kv(key_states, self.num_key_value_groups)
-    value_states = repeat_kv(value_states, self.num_key_value_groups)
-
-    if output_attentions:
-        warnings.warn(
-            "Output attentions is not supported for patched `LlamaAttention`, returning `None` instead."
-        )
-
-    #
-    # sdp-attn start
-    #
-
-    with torch.backends.cuda.sdp_kernel():
-        attn_output = torch.nn.functional.scaled_dot_product_attention(
-            query_states,
-            key_states,
-            value_states,
-            attn_mask=attention_mask,
-            is_causal=False,
-        )
-
-    if attn_output.size() != (bsz, self.num_heads, q_len, self.head_dim):
-        raise ValueError(
-            f"`attn_output` should be of size {(bsz, self.num_heads, q_len, self.head_dim)}, but is"
-            f" {attn_output.size()}"
-        )
-    attn_output = attn_output.transpose(1, 2)
-    attn_output = attn_output.reshape(bsz, q_len, self.hidden_size)
-
-    #
-    # sdp-attn end
-    #
-
-    if self.pretraining_tp > 1:
-        attn_output = attn_output.split(self.hidden_size // self.pretraining_tp, dim=2)
-        o_proj_slices = self.o_proj.weight.split(
-            self.hidden_size // self.pretraining_tp, dim=1
-        )
-        attn_output = sum(
-            F.linear(attn_output[i], o_proj_slices[i])
-            for i in range(self.pretraining_tp)
-        )
-    else:
-        attn_output = self.o_proj(attn_output)
-
-    return attn_output, None, past_key_value
--- a/src/axolotl/monkeypatch/llama_attn_hijack_xformers.py
+++ b/src/axolotl/monkeypatch/llama_attn_hijack_xformers.py
@@ -3,13 +3,12 @@ Directly copied the code from https://raw.githubusercontent.com/oobabooga/text-g
 """

 import logging
-import warnings
+import math
 from typing import Optional, Tuple

 import torch
-import torch.nn.functional as F
 import transformers.models.llama.modeling_llama
-from transformers.models.llama.modeling_llama import apply_rotary_pos_emb, repeat_kv
+from torch import nn

 try:
    import xformers.ops
@@ -21,6 +20,12 @@ def hijack_llama_attention():
    transformers.models.llama.modeling_llama.LlamaAttention.forward = xformers_forward


+def hijack_llama_sdp_attention():
+    transformers.models.llama.modeling_llama.LlamaAttention.forward = (
+        sdp_attention_forward
+    )
+
+
 def xformers_forward(
    self,
    hidden_states: torch.Tensor,
@@ -33,57 +38,30 @@ def xformers_forward(
    # pylint: disable=duplicate-code
    bsz, q_len, _ = hidden_states.size()

-    if not hasattr(self, "pretraining_tp"):
-        self.pretraining_tp = 1
-
-    if self.pretraining_tp > 1:
-        key_value_slicing = (
-            self.num_key_value_heads * self.head_dim
-        ) // self.pretraining_tp
-        query_slices = self.q_proj.weight.split(
-            (self.num_heads * self.head_dim) // self.pretraining_tp, dim=0
-        )
-        key_slices = self.k_proj.weight.split(key_value_slicing, dim=0)
-        value_slices = self.v_proj.weight.split(key_value_slicing, dim=0)
-
-        query_states = [
-            F.linear(hidden_states, query_slices[i]) for i in range(self.pretraining_tp)
-        ]
-        query_states = torch.cat(query_states, dim=-1)
-
-        key_states = [
-            F.linear(hidden_states, key_slices[i]) for i in range(self.pretraining_tp)
-        ]
-        key_states = torch.cat(key_states, dim=-1)
-
-        value_states = [
-            F.linear(hidden_states, value_slices[i]) for i in range(self.pretraining_tp)
-        ]
-        value_states = torch.cat(value_states, dim=-1)
-
-    else:
-        query_states = self.q_proj(hidden_states)
-        key_states = self.k_proj(hidden_states)
-        value_states = self.v_proj(hidden_states)
-
-    query_states = query_states.view(
-        bsz, q_len, self.num_heads, self.head_dim
-    ).transpose(1, 2)
-    key_states = key_states.view(
-        bsz, q_len, self.num_key_value_heads, self.head_dim
-    ).transpose(1, 2)
-    value_states = value_states.view(
-        bsz, q_len, self.num_key_value_heads, self.head_dim
-    ).transpose(1, 2)
-    # [bsz, q_len, nh, hd]
-    # [bsz, nh, q_len, hd]
+    query_states = (
+        self.q_proj(hidden_states)
+        .view(bsz, q_len, self.num_heads, self.head_dim)
+        .transpose(1, 2)
+    )
+    key_states = (
+        self.k_proj(hidden_states)
+        .view(bsz, q_len, self.num_heads, self.head_dim)
+        .transpose(1, 2)
+    )
+    value_states = (
+        self.v_proj(hidden_states)
+        .view(bsz, q_len, self.num_heads, self.head_dim)
+        .transpose(1, 2)
+    )

    kv_seq_len = key_states.shape[-2]
    if past_key_value is not None:
        kv_seq_len += past_key_value[0].shape[-2]
-
    cos, sin = self.rotary_emb(value_states, seq_len=kv_seq_len)
-    query_states, key_states = apply_rotary_pos_emb(
+    (
+        query_states,
+        key_states,
+    ) = transformers.models.llama.modeling_llama.apply_rotary_pos_emb(
        query_states, key_states, cos, sin, position_ids
    )
    # [bsz, nh, t, hd]
@@ -95,61 +73,161 @@ def xformers_forward(

    past_key_value = (key_states, value_states) if use_cache else None

-    # repeat k/v heads if n_kv_heads < n_heads
-    key_states = repeat_kv(key_states, self.num_key_value_groups)
-    value_states = repeat_kv(value_states, self.num_key_value_groups)
+    # We only apply xformers optimizations if we don't need to output the whole attention matrix
+    if not output_attentions:
+        query_states = query_states.transpose(1, 2)
+        key_states = key_states.transpose(1, 2)
+        value_states = value_states.transpose(1, 2)

-    if output_attentions:
-        warnings.warn(
-            "Output attentions is not supported for patched `LlamaAttention`, returning `None` instead."
-        )
-
-    #
-    # xformers-attn start
-    #
-
-    query_states = query_states.transpose(1, 2)
-    key_states = key_states.transpose(1, 2)
-    value_states = value_states.transpose(1, 2)
-
-    # This is a nasty hack. We know attention_mask in transformers is either LowerTriangular or all Zeros.
-    # We therefore check if one element in the upper triangular portion is zero. If it is, then the mask is all zeros.
-    if attention_mask is None or attention_mask[0, 0, 0, 1] == 0:
-        # input and output should be of form (bsz, q_len, num_heads, head_dim)
-        attn_output = xformers.ops.memory_efficient_attention(
-            query_states, key_states, value_states, attn_bias=None
-        )
+        # This is a nasty hack. We know attention_mask in transformers is either LowerTriangular or all Zeros.
+        # We therefore check if one element in the upper triangular portion is zero. If it is, then the mask is all zeros.
+        if attention_mask is None or attention_mask[0, 0, 0, 1] == 0:
+            # input and output should be of form (bsz, q_len, num_heads, head_dim)
+            attn_output = xformers.ops.memory_efficient_attention(
+                query_states, key_states, value_states, attn_bias=None
+            )
+        else:
+            # input and output should be of form (bsz, q_len, num_heads, head_dim)
+            attn_output = xformers.ops.memory_efficient_attention(
+                query_states,
+                key_states,
+                value_states,
+                attn_bias=xformers.ops.LowerTriangularMask(),
+            )
+        attn_weights = None
    else:
-        # input and output should be of form (bsz, q_len, num_heads, head_dim)
-        attn_output = xformers.ops.memory_efficient_attention(
+        attn_weights = torch.matmul(
+            query_states, key_states.transpose(2, 3)
+        ) / math.sqrt(self.head_dim)
+
+        if attn_weights.size() != (bsz, self.num_heads, q_len, kv_seq_len):
+            raise ValueError(
+                f"Attention weights should be of size {(bsz * self.num_heads, q_len, kv_seq_len)}, but is"
+                f" {attn_weights.size()}"
+            )
+
+        if attention_mask is not None:
+            if attention_mask.size() != (bsz, 1, q_len, kv_seq_len):
+                raise ValueError(
+                    f"Attention mask should be of size {(bsz, 1, q_len, kv_seq_len)}, but is {attention_mask.size()}"
+                )
+            attn_weights = attn_weights + attention_mask
+            attn_weights = torch.max(
+                attn_weights, torch.tensor(torch.finfo(attn_weights.dtype).min)
+            )
+
+        # upcast attention to fp32
+        attn_weights = nn.functional.softmax(
+            attn_weights, dim=-1, dtype=torch.float32
+        ).to(query_states.dtype)
+        attn_output = torch.matmul(attn_weights, value_states)
+
+        if attn_output.size() != (bsz, self.num_heads, q_len, self.head_dim):
+            raise ValueError(
+                f"`attn_output` should be of size {(bsz, self.num_heads, q_len, self.head_dim)}, but is"
+                f" {attn_output.size()}"
+            )
+
+        attn_output = attn_output.transpose(1, 2)
+
+    attn_output = attn_output.reshape(bsz, q_len, self.hidden_size)
+    attn_output = self.o_proj(attn_output)
+    return attn_output, attn_weights, past_key_value
+
+
+def sdp_attention_forward(
+    self,
+    hidden_states: torch.Tensor,
+    attention_mask: Optional[torch.Tensor] = None,
+    position_ids: Optional[torch.LongTensor] = None,
+    past_key_value: Optional[Tuple[torch.Tensor]] = None,
+    output_attentions: bool = False,
+    use_cache: bool = False,
+) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]:
+    # pylint: disable=duplicate-code
+    bsz, q_len, _ = hidden_states.size()
+
+    query_states = (
+        self.q_proj(hidden_states)
+        .view(bsz, q_len, self.num_heads, self.head_dim)
+        .transpose(1, 2)
+    )
+    key_states = (
+        self.k_proj(hidden_states)
+        .view(bsz, q_len, self.num_heads, self.head_dim)
+        .transpose(1, 2)
+    )
+    value_states = (
+        self.v_proj(hidden_states)
+        .view(bsz, q_len, self.num_heads, self.head_dim)
+        .transpose(1, 2)
+    )
+
+    kv_seq_len = key_states.shape[-2]
+    if past_key_value is not None:
+        kv_seq_len += past_key_value[0].shape[-2]
+    cos, sin = self.rotary_emb(value_states, seq_len=kv_seq_len)
+    (
+        query_states,
+        key_states,
+    ) = transformers.models.llama.modeling_llama.apply_rotary_pos_emb(
+        query_states, key_states, cos, sin, position_ids
+    )
+    # [bsz, nh, t, hd]
+
+    if past_key_value is not None:
+        # reuse k, v, self_attention
+        key_states = torch.cat([past_key_value[0], key_states], dim=2)
+        value_states = torch.cat([past_key_value[1], value_states], dim=2)
+
+    past_key_value = (key_states, value_states) if use_cache else None
+
+    # We only apply sdp attention if we don't need to output the whole attention matrix
+    if not output_attentions:
+        attn_output = torch.nn.functional.scaled_dot_product_attention(
            query_states,
            key_states,
            value_states,
-            # attn_bias=attention_mask,
-            attn_bias=xformers.ops.LowerTriangularMask(),
+            attn_mask=attention_mask,
+            is_causal=False,
        )
+        attn_weights = None
+    else:
+        attn_weights = torch.matmul(
+            query_states, key_states.transpose(2, 3)
+        ) / math.sqrt(self.head_dim)

-    if attn_output.size() != (bsz, q_len, self.num_heads, self.head_dim):
-        raise ValueError(
-            f"`attn_output` should be of size {(bsz, q_len, self.num_heads, self.head_dim)}, but is"
-            f" {attn_output.size()}"
-        )
+        if attn_weights.size() != (bsz, self.num_heads, q_len, kv_seq_len):
+            raise ValueError(
+                f"Attention weights should be of size {(bsz * self.num_heads, q_len, kv_seq_len)}, but is"
+                f" {attn_weights.size()}"
+            )
+
+        if attention_mask is not None:
+            if attention_mask.size() != (bsz, 1, q_len, kv_seq_len):
+                raise ValueError(
+                    f"Attention mask should be of size {(bsz, 1, q_len, kv_seq_len)}, but is {attention_mask.size()}"
+                )
+            attn_weights = attn_weights + attention_mask
+            attn_weights = torch.max(
+                attn_weights, torch.tensor(torch.finfo(attn_weights.dtype).min)
+            )
+
+        # upcast attention to fp32
+        attn_weights = nn.functional.softmax(
+            attn_weights, dim=-1, dtype=torch.float32
+        ).to(query_states.dtype)
+        attn_output = torch.matmul(attn_weights, value_states)
+
+        if attn_output.size() != (bsz, self.num_heads, q_len, self.head_dim):
+            raise ValueError(
+                f"`attn_output` should be of size {(bsz, self.num_heads, q_len, self.head_dim)}, but is"
+                f" {attn_output.size()}"
+            )
+
+    attn_output = attn_output.transpose(1, 2)
    attn_output = attn_output.reshape(bsz, q_len, self.hidden_size)

-    #
-    # xformers-attn end
-    #
+    attn_output = self.o_proj(attn_output)

-    if self.pretraining_tp > 1:
-        attn_output = attn_output.split(self.hidden_size // self.pretraining_tp, dim=2)
-        o_proj_slices = self.o_proj.weight.split(
-            self.hidden_size // self.pretraining_tp, dim=1
-        )
-        attn_output = sum(
-            F.linear(attn_output[i], o_proj_slices[i])
-            for i in range(self.pretraining_tp)
-        )
-    else:
-        attn_output = self.o_proj(attn_output)
-
-    return attn_output, None, past_key_value
+    return attn_output, attn_weights, past_key_value
--- a/src/axolotl/monkeypatch/llama_expand_mask.py
+++ b/src/axolotl/monkeypatch/llama_expand_mask.py
@@ -1,52 +0,0 @@
-"""
-expands the binary attention mask per 3.2.2 of https://arxiv.org/pdf/2107.02027.pdf
-"""
-from typing import Optional
-
-import torch
-
-
-def _expand_mask(mask: torch.Tensor, dtype: torch.dtype, tgt_len: Optional[int] = None):
-    """
-    Expands attention_mask from `[bsz, seq_len]` to `[bsz, 1, tgt_seq_len, src_seq_len]`.
-    This expansion handles packed sequences so that sequences share the same attention mask integer value
-    when they attend to each other within that sequence.
-    This expansion transforms the mask to lower triangular form to prevent future peeking.
-    """
-    bsz, src_len = mask.size()
-    tgt_len = tgt_len if tgt_len is not None else src_len
-
-    mask = mask.unsqueeze(1).unsqueeze(2)
-    mask = mask.expand(bsz, 1, tgt_len, src_len)
-
-    # Create a binary mask from the original mask where zeros remain zeros and all other values are set to one
-    binary_mask = torch.where(
-        mask != 0,
-        torch.tensor(1).to(dtype),
-        torch.tensor(0).to(dtype),
-    )
-
-    # Create a block-diagonal mask.
-    # we multiply by the binary mask so that 0's in the original mask are correctly excluded
-    zero_one_mask = torch.eq(mask, mask.transpose(-1, -2)).int() * binary_mask
-
-    # Now let's create a lower triangular mask of ones that will zero out the upper triangular part
-    lower_triangular_ones = torch.tril(torch.ones((tgt_len, src_len), dtype=dtype)).to(
-        mask.device
-    )
-
-    # Use the lower triangular mask to zero out the upper triangular part of the zero_one_mask
-    masked_zero_one_mask = zero_one_mask * lower_triangular_ones
-    inverted_mask = 1.0 - masked_zero_one_mask
-
-    return inverted_mask.masked_fill(
-        inverted_mask.to(torch.bool), torch.finfo(dtype).min
-    )
-
-
-def hijack_expand_mask():
-    import transformers
-
-    transformers.models.llama.modeling_llama._expand_mask = (  # pylint: disable=protected-access
-        _expand_mask
-    )
--- a/src/axolotl/monkeypatch/llama_landmark_attn.py
+++ b/src/axolotl/monkeypatch/llama_landmark_attn.py
@@ -53,7 +53,7 @@ from transformers.utils import (
    replace_return_docstrings,
 )

-LOG = logging.getLogger("axolotl")
+logger = logging.get_logger(__name__)

 _CONFIG_FOR_DOC = "LlamaConfig"

@@ -862,7 +862,7 @@ class LlamaModel(LlamaPreTrainedModel):

        if self.gradient_checkpointing and self.training:
            if use_cache:
-                LOG.warning_once(
+                logger.warning_once(
                    "`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`..."
                )
                use_cache = False
--- a/src/axolotl/monkeypatch/relora.py
+++ b/src/axolotl/monkeypatch/relora.py
@@ -1,393 +0,0 @@
-"""Implements the ReLoRA training procedure from https://arxiv.org/abs/2307.05695, minus the initial full fine-tune."""
-import glob
-import json
-import logging
-import os.path
-import shutil
-from pathlib import Path
-from typing import Dict, List, Sequence
-
-import bitsandbytes as bnb
-import peft
-import safetensors.torch as st
-import torch
-from huggingface_hub import snapshot_download
-from torch.optim.lr_scheduler import LRScheduler
-from torch.optim.optimizer import Optimizer
-from transformers import (
-    TrainerCallback,
-    TrainerControl,
-    TrainerState,
-    TrainingArguments,
-)
-from transformers.trainer_utils import PREFIX_CHECKPOINT_DIR
-
-from axolotl.utils.dict import DictDefault
-from axolotl.utils.distributed import is_main_process
-
-LOG = logging.getLogger("axolotl.relora")
-
-
-def reset_optimizer(optimizer: torch.optim.Optimizer):
-    for group in optimizer.param_groups:
-        for param in group["params"]:
-            param_state = optimizer.state[param]
-            for key in param_state:
-                if "qmap" in key:
-                    continue
-
-                if key == "step" and isinstance(param_state[key], int):
-                    param_state[key] = 0
-                else:
-                    param_state[key] = torch.zeros_like(param_state[key])
-
-
-class ReLoRACallback(TrainerCallback):
-    """Callback to merge LoRA weights into the base model and save full-weight checkpoints"""
-
-    def __init__(self, cfg: DictDefault):
-        self.relora_steps = cfg.relora_steps
-        self.cpu_offload = cfg.relora_cpu_offload
-        self.quantized = cfg.load_in_4bit or cfg.load_in_8bit
-        self.last_full_model = cfg.base_model
-        self.resume_from_checkpoint = cfg.resume_from_checkpoint
-
-        if not os.path.exists(self.last_full_model):
-            self.last_full_model = str(Path(snapshot_download(cfg.base_model)))
-
-        assert os.path.exists(
-            self.last_full_model
-        ), "for ReLORA base_model must be a local path"
-
-        self.num_lora_restarts = 0
-        self.need_full_save = False
-
-    def on_train_begin(
-        self,
-        _args: TrainingArguments,
-        _state: TrainerState,
-        control: TrainerControl,
-        model: peft.LoraModel,
-        **_kwargs,
-    ):
-        if self.resume_from_checkpoint:
-            weight_path = os.path.join(self.resume_from_checkpoint, "relora")
-            if not os.path.exists(weight_path):
-                LOG.warning(
-                    "Resuming ReLoRA from checkpoint, but no full-weight save found"
-                )
-            else:
-                LOG.info(f"Loading adjusted base weights from {weight_path}")
-                load_weight_checkpoint(model, weight_path)
-        return control
-
-    def on_step_begin(
-        self,
-        args: TrainingArguments,
-        state: TrainerState,
-        control: TrainerControl,
-        model: peft.LoraModel,
-        optimizer: torch.optim.Optimizer,
-        **_kwargs,
-    ):
-        if state.global_step > 0 and state.global_step % self.relora_steps == 0:
-            checkpoint_folder = os.path.join(
-                args.output_dir,
-                f"{PREFIX_CHECKPOINT_DIR}-{state.global_step}",
-                "relora",
-            )
-
-            with torch.no_grad():
-                merge_and_save(
-                    model,
-                    self.last_full_model,
-                    checkpoint_folder,
-                    reinit=True,
-                    quantized=self.quantized,
-                    actually_save=is_main_process(),
-                    cpu_offload=self.cpu_offload,
-                )
-                reset_optimizer(optimizer)
-
-            if self.quantized:
-                self.last_full_model = checkpoint_folder
-            self.num_lora_restarts += 1
-
-        return control
-
-    def on_save(
-        self,
-        args: TrainingArguments,
-        state: TrainerState,
-        control: TrainerControl,
-        model: peft.LoraModel,
-        **_kwargs,
-    ):
-        checkpoint_folder = os.path.join(
-            args.output_dir, f"{PREFIX_CHECKPOINT_DIR}-{state.global_step}", "relora"
-        )
-        if (
-            state.global_step >= self.relora_steps
-            and state.global_step % self.relora_steps != 0
-        ):
-            if self.quantized:
-                if is_main_process() and self.last_full_model != checkpoint_folder:
-                    # ensure the latest full parameter save is in the latest checkpoint
-                    # folder, so that automatic pruning of checkpoints does not remove it
-                    LOG.info(f"moving last full parameter save to {checkpoint_folder}")
-                    os.makedirs(checkpoint_folder, exist_ok=True)
-                    chunks = glob.glob(
-                        f"{self.last_full_model}/model*.safetensors"
-                    ) + glob.glob(f"{self.last_full_model}/model*.index.json")
-                    for path in chunks:
-                        new_path = os.path.abspath(shutil.move(path, checkpoint_folder))
-                        try:
-                            os.symlink(new_path, path)
-                        except OSError:
-                            # probably on windows without permission to symlink
-                            pass
-
-                    self.last_full_model = checkpoint_folder
-            else:
-                model.model.save_pretrained(checkpoint_folder, safe_serialization=True)
-
-        return control
-
-    def on_log(
-        self,
-        _args: TrainingArguments,
-        _state: TrainerState,
-        control: TrainerControl,
-        logs: Dict[str, float],
-        **_kwargs,
-    ):
-        logs["num_lora_restarts"] = self.num_lora_restarts
-        return control
-
-    def on_train_end(
-        self,
-        args: TrainingArguments,
-        _state: TrainerState,
-        control: TrainerControl,
-        model: peft.LoraModel,
-        **_kwargs,
-    ):
-        if self.quantized:
-            # perform final merge and save
-            with torch.no_grad():
-                merge_and_save(
-                    model,
-                    self.last_full_model,
-                    args.output_dir,
-                    reinit=False,
-                    quantized=self.quantized,
-                    actually_save=is_main_process(),
-                    cpu_offload=self.cpu_offload,
-                )
-        # no need to save if unquantized, as finetune.py will call merge_and_unload()
-        return control
-
-
-class ReLoRAScheduler(LRScheduler):
-    """Wraps another scheduler to apply per-lora-restart learning rate warmups."""
-
-    def __init__(
-        self,
-        optimizer: Optimizer,
-        inner_schedule: LRScheduler,
-        relora_steps: int,
-        warmup_steps: int,
-        min_lr_scale: float = 0.001,
-    ) -> None:
-        self.inner_schedule = inner_schedule
-        self.relora_steps = relora_steps
-        self.warmup_steps = warmup_steps
-        self.min_lr_scale = min_lr_scale
-        super().__init__(optimizer, inner_schedule.last_epoch, inner_schedule.verbose)
-
-    def get_lr(self) -> float:
-        self.inner_schedule.last_epoch = self.last_epoch
-
-        original = self.inner_schedule.get_lr()
-        step = self.last_epoch
-        if step < self.relora_steps:
-            scale = 1
-        else:
-            cycle_t = min(1.0, (step % self.relora_steps) / self.warmup_steps)
-            scale = cycle_t * (1 - self.min_lr_scale) + self.min_lr_scale
-
-        if isinstance(original, Sequence):
-            return [lr * scale for lr in original]
-        return original * scale
-
-
-def sharded_paths(path: str, module_names: List[str]) -> Dict[str, str]:
-    model_name = "model.safetensors"
-    if not os.path.exists(str(Path(path) / model_name)) and not os.path.exists(
-        str(Path(path) / f"{model_name}.index.json")
-    ):
-        model_name = "pytorch_model.bin"
-
-    index_path = str(Path(path) / f"{model_name}.index.json")
-    if os.path.exists(index_path):
-        with open(index_path, "r", encoding="utf-8") as file:
-            data = json.load(file)
-        return data["weight_map"]
-    return {(module_name + ".weight"): model_name for module_name in module_names}
-
-
-def lora_delta_weight(layer: peft.tuners.lora.LoraLayer, device) -> torch.Tensor:
-    if isinstance(layer, (peft.tuners.lora.Linear8bitLt, peft.tuners.lora.Linear4bit)):
-        adapter = layer.active_adapter
-        return (
-            peft.utils.transpose(
-                layer.lora_B[adapter].weight.detach().to(device)
-                @ layer.lora_A[adapter].weight.detach().to(device),
-                getattr(layer, "fan_in_fan_out", False),
-            )
-            * layer.scaling[adapter]
-        )
-
-    return layer.get_delta_weight().to(device)
-
-
-def find_lora_modules(model: peft.LoraModel) -> Dict[str, peft.tuners.lora.LoraLayer]:
-    modules: Dict[str, peft.tuners.lora.LoraLayer] = {}
-
-    key_list = [key for key, _ in model.model.named_modules() if "lora" not in key]
-    for key in key_list:
-        try:
-            # pylint: disable=protected-access
-            _parent, target, _target_name = peft.utils._get_submodules(model.model, key)
-        except AttributeError:
-            continue
-
-        if isinstance(target, peft.tuners.lora.LoraLayer):
-            modules[key] = target
-
-    return modules
-
-
-def update_weights(
-    target: peft.tuners.lora.LoraLayer, new_weight: torch.Tensor, reinit: bool, device
-):
-    if reinit:
-        for adapter_name in target.lora_A:
-            target.reset_lora_parameters(adapter_name)
-        for adapter_name in target.lora_embedding_A:
-            target.reset_lora_parameters(adapter_name)
-
-    if isinstance(target, peft.tuners.lora.Linear4bit):
-        # This could be faster, but the quantization of Linear4bit weights occurs
-        # when the module is moved from cpu to gpu. Without meddling *too* deeply in
-        # PEFT's innards or maintaining a duplicate of that codepath, this is good
-        # enough for now.
-        target.weight.quant_state = None
-        target.weight.data = new_weight.cpu()
-        target.to(device)
-    elif isinstance(target, peft.tuners.lora.Linear8bitLt):
-        target.weight = bnb.nn.Int8Params(new_weight, requires_grad=False).to(device)
-    else:
-        target.weight.data = new_weight.to(device)
-
-
-def merge_and_save(
-    model: peft.LoraModel,
-    model_src: str,
-    model_dst: str,
-    reinit: bool = False,
-    quantized: bool = False,
-    cpu_offload: bool = False,
-    actually_save: bool = True,
-):
-    modules = find_lora_modules(model)
-
-    if not quantized:
-        for module_name, target in modules.items():
-            update = target.get_delta_weight(target.active_adapter).detach()
-            target.weight.data += update
-
-            if reinit:
-                for adapter_name in target.lora_A:
-                    target.reset_lora_parameters(adapter_name)
-                for adapter_name in target.lora_embedding_A:
-                    target.reset_lora_parameters(adapter_name)
-        return
-
-    os.makedirs(model_dst, exist_ok=True)
-    shard_paths = sharded_paths(model_src, modules.keys())
-    out_shard_paths = {}
-
-    unique_shards = list(set(shard_paths.values()))
-    for shard_path in unique_shards:
-        out_tensors = {}
-        if shard_path.endswith(".safetensors"):
-            in_tensors = st.load_file(str(Path(model_src) / shard_path))
-        else:
-            in_tensors = torch.load(Path(model_src) / shard_path)
-            if "state_dict" in in_tensors:
-                in_tensors = in_tensors["state_dict"]
-
-        for module_name, target in modules.items():
-            key = module_name + ".weight"
-            if key not in shard_paths or shard_paths[key] != shard_path:
-                continue
-
-            orig_weight = in_tensors[key]
-            old_dev = target.weight.device
-            math_dev = "cpu" if cpu_offload else old_dev
-
-            delta_weight = lora_delta_weight(target, math_dev)
-            new_weight = orig_weight.to(math_dev) + delta_weight
-            del delta_weight
-
-            if actually_save:
-                out_tensors[key] = new_weight.half().cpu()
-
-            update_weights(target, new_weight, reinit=reinit, device=old_dev)
-
-        if actually_save:
-            out_shard_name = shard_path
-            if out_shard_name.startswith("pytorch_model"):
-                out_shard_name = (
-                    out_shard_name.replace("pytorch_model", "model").rstrip(".bin")
-                    + ".safetensors"
-                )
-
-            for module_name in in_tensors:
-                if module_name not in out_tensors:
-                    out_tensors[module_name] = in_tensors[module_name].half()
-                out_shard_paths[module_name] = out_shard_name
-
-            shard_fn = str(Path(model_dst) / out_shard_name)
-            LOG.info(f"saving tensors to {shard_fn}")
-            st.save_file(out_tensors, shard_fn, metadata={"format": "pt"})
-
-        del in_tensors
-        del out_tensors
-        torch.cuda.empty_cache()
-
-    if actually_save and len(unique_shards) > 1:
-        with open(
-            str(Path(model_dst, "model.safetensors.index.json")), "w", encoding="utf-8"
-        ) as file:
-            json.dump({"metadata": {}, "weight_map": out_shard_paths}, file)
-
-
-def load_weight_checkpoint(model: peft.LoraModel, checkpoint_path: str):
-    modules = find_lora_modules(model)
-    shard_paths = sharded_paths(checkpoint_path, modules.keys())
-    unique_shards = list(set(shard_paths.values()))
-
-    for shard_path in unique_shards:
-        tensors = st.load_file(os.path.join(checkpoint_path, shard_path))
-
-        for module_name, target in modules.items():
-            key = module_name + ".weight"
-            if key not in shard_paths or shard_paths[key] != shard_path:
-                continue
-
-            new_weight = tensors[key]
-            update_weights(
-                target, new_weight, reinit=False, device=target.weight.device
-            )
--- a/src/axolotl/monkeypatch/utils.py
+++ b/src/axolotl/monkeypatch/utils.py
@@ -1,103 +0,0 @@
-"""
-Shared utils for the monkeypatches
-"""
-import torch
-
-
-def get_cu_seqlens(attn_mask):
-    """generate a cumulative sequence length mask for flash attention using attn mask"""
-    if len(attn_mask.shape) == 1:
-        attn_mask = attn_mask.unsqueeze(0)
-
-    device = attn_mask.device
-    results = []
-    max_seq_lens = []
-
-    for row in attn_mask:
-        # Exclude zeros to avoid adding their positions to the mask
-        t_non_zeros = row[row != 0]
-        # Find where the sequence number changes (including the first position)
-        seq_change = torch.cat(
-            [
-                torch.tensor([1], dtype=torch.int32, device=device),
-                t_non_zeros[1:] != t_non_zeros[:-1],
-            ]
-        )
-        # Get the indices where the sequence changes
-        change_indices = torch.cat(
-            [
-                (seq_change == 1).nonzero(as_tuple=True)[0],
-                torch.tensor([len(t_non_zeros)], dtype=torch.int32, device=device),
-            ]
-        )
-        # Calculate the sequence lengths
-        seq_lengths = change_indices[1:] - change_indices[:-1]
-        # Calculate the length of the final sequence or padding
-        final_seq_length = len(row) - change_indices[-1]
-        # Append the length of the final sequence or padding to seq_lengths
-        if final_seq_length.item():
-            seq_lengths = torch.cat(
-                [
-                    seq_lengths,
-                    torch.tensor(
-                        [final_seq_length.item()], dtype=torch.int32, device=device
-                    ),
-                ]
-            )
-        # Calculate the cumulative sequence lengths
-        cu_seqlens = torch.cat(
-            [torch.tensor([0], dtype=torch.int32, device=device), seq_lengths.cumsum(0)]
-        )
-        max_seq_len = (cu_seqlens[1:] - cu_seqlens[:-1]).max()
-        results.append(cu_seqlens)
-        max_seq_lens.append(max_seq_len)
-
-    return torch.stack(results).to(dtype=torch.int32), torch.stack(max_seq_lens)
-
-
-def get_cu_seqlens_from_pos_ids(position_ids):
-    """generate a cumulative sequence length mask for flash attention using pos ids"""
-    if len(position_ids.shape) == 1:
-        position_ids = position_ids.unsqueeze(0)
-
-    device = position_ids.device
-    results = []
-    max_seq_lens = []
-
-    for row in position_ids:
-        # Count the number of consecutive zeros from the right side
-        padding_length = (row == 0).int().flip(dims=[0]).cumprod(dim=0).sum().item()
-
-        # Adjust the row to exclude padding
-        adjusted_row = row[:-padding_length] if padding_length else row.clone()
-
-        # Find where the position resets to 0 (indicating a new sequence)
-        seq_starts = torch.cat(
-            [
-                torch.tensor([True], dtype=torch.bool, device=device),
-                adjusted_row[1:] == 0,
-            ]
-        )
-        # Get the indices where the sequence starts
-        start_indices = torch.cat(
-            [
-                (seq_starts).nonzero(as_tuple=True)[0],
-                torch.tensor([len(adjusted_row)], dtype=torch.int32, device=device),
-            ]
-        )
-        # Calculate the sequence lengths
-        seq_lengths = start_indices[1:] - start_indices[:-1]
-        # Calculate the cumulative sequence lengths
-        cu_seqlens = torch.cat(
-            [torch.tensor([0], dtype=torch.int32, device=device), seq_lengths.cumsum(0)]
-        )
-        # Append the padding length to the cumulative sequence lengths
-        if padding_length:
-            cu_seqlens = torch.cat(
-                [cu_seqlens, torch.tensor([len(row)], dtype=torch.int32, device=device)]
-            )
-        max_seq_len = (cu_seqlens[1:] - cu_seqlens[:-1]).max()
-        results.append(cu_seqlens)
-        max_seq_lens.append(max_seq_len)
-
-    return torch.stack(results).to(dtype=torch.int32), torch.stack(max_seq_lens)
--- a/src/axolotl/prompt_strategies/init.py
+++ b/src/axolotl/prompt_strategies/init.py
@@ -2,10 +2,8 @@

 import importlib

-from axolotl.prompt_strategies.user_defined import UserDefinedDatasetConfig

-
-def load(strategy, tokenizer, cfg, ds_cfg):
+def load(strategy, tokenizer, cfg):
    try:
        load_fn = "load"
        if strategy.split(".")[-1].startswith("load_"):
@@ -13,9 +11,6 @@ def load(strategy, tokenizer, cfg, ds_cfg):
            strategy = ".".join(strategy.split(".")[:-1])
        mod = importlib.import_module(f".{strategy}", "axolotl.prompt_strategies")
        func = getattr(mod, load_fn)
-        load_kwargs = {}
-        if strategy == "user_defined":
-            load_kwargs["ds_cfg"] = UserDefinedDatasetConfig(**ds_cfg)
-        return func(tokenizer, cfg, **load_kwargs)
+        return func(tokenizer, cfg)
    except Exception:  # pylint: disable=broad-exception-caught
        return None
--- a/src/axolotl/prompt_strategies/alpaca_w_system.py
+++ b/src/axolotl/prompt_strategies/alpaca_w_system.py
@@ -57,8 +57,6 @@ class SystemDataPrompter(AlpacaPrompter):
    Alpaca Style Prompter that uses system prompts from the dataset
    """

-    system_format: str = "### System:\n{system}\n\n"
-
    def build_prompt_w_system(
        self,
        system: str,
@@ -68,47 +66,15 @@ class SystemDataPrompter(AlpacaPrompter):
    ) -> Generator[str, None, None]:
        # returns the full prompt from instruction and optional input
        # if a label (=response, =output) is provided, it's also appended.
-        formatted_sys_prompt = (
-            self.system_format.format(system=system)
-            if system and self.system_format
-            else ""
-        )
        if input:
-            res = formatted_sys_prompt + self.turn_format.format(
-                instruction=instruction, input=input
-            )
+            res = system + self.turn_format.format(instruction=instruction, input=input)
        else:
-            res = formatted_sys_prompt + self.turn_no_input_format.format(
-                instruction=instruction
-            )
+            res = system + self.turn_no_input_format.format(instruction=instruction)
        if output:
            res = f"{res}{output}"
        yield res


-class OpenOrcaSystemDataPrompter(SystemDataPrompter):
-    """
-    Alpaca Style Prompter that uses system prompts from the dataset, with OpenOrca prompts
-    """
-
-    def match_prompt_style(self):
-        # pylint: disable=duplicate-code
-        if self.prompt_style == PromptStyle.INSTRUCT.value:
-            self.turn_format = "### Human:\n{instruction}\n### Additional Context:\n{input}\n### Assistant:\n"
-            self.turn_no_input_format = "### Human:\n{instruction}\n### Assistant:\n"
-            self.system_format = "### System:\n{system}\n"
-        if self.prompt_style == PromptStyle.CHAT.value:
-            self.turn_format = "USER: {instruction}\n{input}\nASSISTANT:"
-            self.turn_no_input_format = "USER: {instruction}\nASSISTANT:"
-            self.system_format = "SYSTEM: {system}\n"
-        if self.prompt_style == PromptStyle.CHATML.value:
-            self.turn_format = "<|im_start|>user\n{instruction}\n{input}<|im_end|>\n<|im_start|>assistant\n"
-            self.turn_no_input_format = (
-                "<|im_start|>user\n{instruction}<|im_end|>\n<|im_start|>assistant\n"
-            )
-            self.system_format = "<|im_start|>system\n{system}<|im_end|>\n"
-
-
 class OpenOrcaPromptTokenizingStrategy(InstructionWSystemPromptTokenizingStrategy):
    """
    Tokenizing strategy for OpenOrca datasets
@@ -147,16 +113,7 @@ def load_chat(tokenizer, cfg):

 def load_open_orca(tokenizer, cfg):
    return OpenOrcaPromptTokenizingStrategy(
-        OpenOrcaSystemDataPrompter(PromptStyle.INSTRUCT.value),
-        tokenizer,
-        cfg.train_on_inputs,
-        cfg.sequence_len,
-    )
-
-
-def load_open_orca_chatml(tokenizer, cfg):
-    return OpenOrcaPromptTokenizingStrategy(
-        OpenOrcaSystemDataPrompter(PromptStyle.CHATML.value),
+        SystemDataPrompter(PromptStyle.INSTRUCT.value),
        tokenizer,
        cfg.train_on_inputs,
        cfg.sequence_len,
--- a/src/axolotl/prompt_strategies/llama2_chat.py
+++ b/src/axolotl/prompt_strategies/llama2_chat.py
@@ -1,205 +0,0 @@
-"""
-Prompt Strategy for finetuning Llama2 chat models
-see also https://github.com/facebookresearch/llama/blob/6c7fe276574e78057f917549435a2554000a876d/llama/generation.py#L213 for ma reference implementation.
-
-This implementation is based on the Vicuna PR and the fastchat repo, see also:
-https://github.com/lm-sys/FastChat/blob/cdd7730686cb1bf9ae2b768ee171bdf7d1ff04f3/fastchat/conversation.py#L847
-
-Use dataset type: "llama2_chat" in conig.yml to use this prompt style.
-
-E.g. in the config.yml:
-```
-datasets:
-  - path: llama_finetune_train.jsonl
-    type: llama2_chat
-```
-
-The dataset itself should look like this:
-```
-{'conversations':[{"from": "human", "value": "Who are you?"}, {"from": "gpt", "value": "I am Vicuna"},...]}
-```
-in a jsonl file. The first message should be from the human, the second from gpt.
-For a custom system message, the first "from" can be "system" (followed by alternating "human" and "gpt" turns).
-
-Important: Don't use "special_tokens:" in your config.yml if you are not sure what you are doing!
-"""
-
-import logging
-from dataclasses import dataclass, field
-from typing import Generator, List, Sequence
-
-from axolotl.prompt_tokenizers import PromptTokenizingStrategy
-from axolotl.prompters import IGNORE_TOKEN_ID, SHAREGPT_ASSERTION_FAILED_ROLE
-
-
-@dataclass
-class Llama2ChatConversation:
-    """A class that manages prompt templates and keeps all conversation history.
-    copied from https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py"""
-
-    name: str = "llama2"
-    # The system prompt
-    system: str = (
-        "[INST] <<SYS>>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. "
-        "Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. "
-        "Please ensure that your responses are socially unbiased and positive in nature.\n\n"
-        "If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. "
-        "If you don't know the answer to a question, please don't share false information.\n<</SYS>>\n\n"
-    )
-    roles: Sequence[str] = ("[INST]", "[/INST]")
-    messages: List[List[str]] = field(default_factory=list)
-    offset: int = 0
-    sep = " "
-    sep2 = " </s><s>"
-    stop_token_ids = [2]
-
-    def get_prompt(self) -> str:
-        """Get the prompt for generation."""
-        seps = [self.sep, self.sep2]
-        ret = ""
-        for i, (role, message) in enumerate(self.messages):
-            if (i == len(self.messages) - 1) and (role == self.roles[0]):
-                # last message is from user (due to length),
-                #  return prompt without it for training
-                return ret
-            if i == 0:
-                ret += self.system + message.strip()
-            else:
-                ret += role + " " + message.strip() + seps[i % 2]
-        return ret
-
-    def append_message(self, role: str, message: str):
-        """Append a new message."""
-        self.messages.append([role, message])
-
-
-class LLama2ChatTokenizingStrategy(PromptTokenizingStrategy):
-    """
-    Tokenizing strategy for ShareGPT prompts.
-    adapted from https://github.com/lm-sys/FastChat/blob/main/fastchat/train/train.py
-    """
-
-    def __init__(self, *args, **kwargs):
-        super().__init__(*args, **kwargs)
-        self.sequence_len = 4096
-        self.tokenizer.add_special_tokens({"pad_token": "<pad>"})
-        # https://huggingface.co/meta-llama/Llama-2-7b-chat-hf/blob/main/added_tokens.json
-
-    def tokenize_prompt(self, prompt):
-        conv = next(self.prompter.build_prompt(prompt))
-        conversation_str = conv.get_prompt()
-
-        # Tokenize conversations
-        input_ids = self.tokenizer(
-            conversation_str,
-            return_tensors="pt",
-            padding="max_length",
-            max_length=self.sequence_len,
-            truncation=True,
-        ).input_ids[0]
-        target = input_ids.clone()
-
-        # Mask targets. Only compute loss on the assistant outputs.
-        sep = conv.roles[1]
-
-        total_len = int(target.ne(self.tokenizer.pad_token_id).sum())
-
-        turns = conversation_str.split(conv.sep2)
-        cur_len = 1
-        target[:cur_len] = IGNORE_TOKEN_ID
-        for turn in turns:
-            if turn == "":
-                break
-            turn_len = len(self.tokenizer(turn).input_ids)
-
-            parts = turn.split(sep)
-            if len(parts) != 2:
-                break
-            parts[0] += sep
-            # "-1" is hardcoded for the LLaMA tokenizer to make the offset correct.
-            instruction_len = len(self.tokenizer(parts[0]).input_ids) - 1
-
-            # Ignore the user instructions
-            target[cur_len - 1 : cur_len + instruction_len] = IGNORE_TOKEN_ID
-            cur_len += turn_len + 2  # due to length of role token
-
-        target[cur_len:] = IGNORE_TOKEN_ID
-
-        if cur_len < self.sequence_len:
-            if cur_len != total_len:
-                target[:] = IGNORE_TOKEN_ID
-                logging.warning(
-                    f"WARNING: tokenization mismatch: {cur_len} vs. {total_len}."
-                    f" (ignored)"
-                )
-
-        attention_mask = input_ids.ne(self.tokenizer.pad_token_id).tolist()
-        input_ids = input_ids.tolist()
-        target = target.tolist()
-        # this is a fix for the tokenizer which tokenizes [ differently with eos tokens and
-        # follows the original llama implementation
-        for i in range(2, total_len - 2):
-            if input_ids[i] == 29961:
-                input_ids[i] = 518
-            if target[i] == 29961:
-                target[i] = 518
-        return {
-            "input_ids": input_ids,
-            "labels": target,
-            "attention_mask": attention_mask,
-        }
-
-
-class Llama2ChatPrompter:  # pylint: disable=too-few-public-methods
-    """
-    A prompter that generates prompts for Llama2 models.
-    """
-
-    system_prompt = (
-        "[INST] <<SYS>>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. "
-        "Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. "
-        "Please ensure that your responses are socially unbiased and positive in nature.\n\n"
-        "If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. "
-        "If you don't know the answer to a question, please don't share false information.\n<</SYS>>\n\n"
-    )
-
-    def build_prompt(self, source) -> Generator[Llama2ChatConversation, None, None]:
-        # see https://github.com/lm-sys/FastChat/blob/da0641e567cf93756b0978ab5a6b092e96f06240/fastchat/train/train.py#L78
-        source = source["conversations"]  # fix data structure for datasets
-
-        # if system prompt provided, use it
-        if source[0]["from"] == "system":
-            system = f"[INST] <<SYS>>\n{source[0]['value']}\n<</SYS>>\n\n"
-            source = source[1:]
-        else:
-            system = self.system_prompt
-
-        conv = Llama2ChatConversation(system=system)
-
-        if len(source) < 2:
-            # If there isn't a back and forth conversation, ignore it
-            # also happens on the data splitting leaving empty conversations
-            raise IndexError
-
-        roles = {"human": conv.roles[0], "gpt": conv.roles[1]}
-
-        if roles[source[0]["from"]] != conv.roles[0]:
-            # Skip the first one if it is not from human
-            source = source[1:]
-
-        conv.messages = []  # pylint: disable=R0801
-        for j, sentence in enumerate(source):
-            role = roles[sentence["from"]]
-            assert role == conv.roles[j % 2], SHAREGPT_ASSERTION_FAILED_ROLE
-            if sentence["value"]:
-                conv.append_message(role, sentence["value"])
-        yield conv
-
-
-def load(tokenizer, cfg) -> LLama2ChatTokenizingStrategy:
-    return LLama2ChatTokenizingStrategy(
-        Llama2ChatPrompter(),
-        tokenizer,
-        cfg.train_on_inputs,
-        cfg.sequence_len,
-    )
--- a/src/axolotl/prompt_strategies/metharme.py
+++ b/src/axolotl/prompt_strategies/metharme.py
@@ -1,76 +0,0 @@
-"""Module containing the MetharmenPromptTokenizingStrategy and MetharmePrompter class"""
-
-import logging
-from typing import Tuple
-
-from axolotl.prompt_tokenizers import InstructionPromptTokenizingStrategy
-from axolotl.prompters import AlpacaPrompter
-
-LOG = logging.getLogger("axolotl")
-
-IGNORE_TOKEN_ID = -100
-
-# pylint: disable=duplicate-code
-
-
-class MetharmePromptTokenizingStrategy(InstructionPromptTokenizingStrategy):
-    """
-    Tokenizing strategy for the Metharme models
-    """
-
-    def parse_instruction_fields(self, prompt) -> Tuple[str, str, str]:
-        return (prompt["prompt"], "", prompt["generation"])
-
-    def _tokenize(
-        self,
-        prompt: str,
-        add_eos_token: bool = True,
-        strip_bos_token: bool = False,
-        num_eos_tokens: int = 3,
-    ):
-        result = self.tokenizer(
-            prompt,
-            truncation=True,
-            max_length=self.sequence_len,
-            padding=False,
-            return_tensors=None,
-        )
-        if len(result["input_ids"]) == 0:
-            LOG.warning("Tokenizer result is empty. You may want to audit your dataset")
-        # If there's already an EOS token there, subtract from the number added
-        if result["input_ids"][-1] == self.tokenizer.eos_token_id:
-            num_eos_tokens -= 1
-
-        if num_eos_tokens > 0 and add_eos_token and len(result["input_ids"]) > 0:
-            for _ in range(num_eos_tokens):
-                if len(result["input_ids"]) < self.sequence_len:
-                    result["input_ids"].append(self.tokenizer.eos_token_id)
-                    result["attention_mask"].append(1)
-
-        if result["input_ids"][0] == self.tokenizer.bos_token_id and strip_bos_token:
-            result["input_ids"] = result["input_ids"][1:]
-            result["attention_mask"] = result["attention_mask"][1:]
-
-        result["labels"] = result["input_ids"].copy()
-        return result
-
-
-class MetharmePrompter(AlpacaPrompter):
-    """
-    Prompter for the Metharme models.
-    """
-
-    system_prompt = ""
-    system_no_input_prompt = ""
-    system_format = ""
-    turn_format = "{instruction}"
-    turn_no_input_format = "{instruction}"
-
-    def __init__(self, *args, **kwargs):  # pylint: disable=super-init-not-called
-        pass
-
-
-def load(tokenizer, cfg):
-    return MetharmePromptTokenizingStrategy(
-        MetharmePrompter(), tokenizer, cfg.train_on_inputs, cfg.sequence_len
-    )
--- a/src/axolotl/prompt_strategies/orcamini.py
+++ b/src/axolotl/prompt_strategies/orcamini.py
@@ -1,46 +0,0 @@
-"""
-Prompt Strategy for finetuning Orca Mini (v2) models
-see also https://huggingface.co/psmathur/orca_mini_v2_7b for more information
-
-Use dataset type: orcamini in conig.yml to use this prompt style.
-
-Compared to the alpaca_w_system.open_orca dataset type,
-this one specifies the system prompt with "### System:".
-
-Not suited/tested for multiple-turn conversations without further adjustments.
-"""
-from typing import Generator, Union
-
-from axolotl.prompt_strategies.alpaca_w_system import OpenOrcaPromptTokenizingStrategy
-from axolotl.prompters import AlpacaPrompter
-
-
-class OrcaMiniPrompter(AlpacaPrompter):
-    """Adjusted Prompter for Orca Mini (v2) datasets"""
-
-    def match_prompt_style(self):
-        self.turn_no_input_format = (
-            "### System:\n{system}\n\n### User:\n{instruction}\n\n### Response:\n"
-        )
-
-    def build_prompt_w_system(
-        self,
-        system: str,
-        instruction: str,
-        output: Union[None, str] = None,
-    ) -> Generator[str, None, None]:
-        # returns the full prompt from instruction and optional input
-        # if a label (=response, =output) is provided, it's also appended.
-        res = self.turn_no_input_format.format(system=system, instruction=instruction)
-        if output:
-            res = f"{res}{output}"
-        yield res
-
-
-def load(tokenizer, cfg):
-    return OpenOrcaPromptTokenizingStrategy(
-        OrcaMiniPrompter(),
-        tokenizer,
-        cfg.train_on_inputs,
-        cfg.sequence_len,
-    )
--- a/src/axolotl/prompt_strategies/pygmalion.py
+++ b/src/axolotl/prompt_strategies/pygmalion.py
@@ -11,8 +11,6 @@ from axolotl.prompt_tokenizers import (
    tokenize_prompt_default,
 )

-LOG = logging.getLogger("axolotl")
-
 IGNORE_TOKEN_ID = -100


@@ -66,7 +64,7 @@ class PygmalionPromptTokenizingStrategy(PromptTokenizingStrategy):
                    *copy.deepcopy(res["input_ids"])
                ][len(self.bot_prefix_token_ids) :]
            else:
-                LOG.warning(f"unknown role in conversation: {role}")
+                logging.warning(f"unknown role in conversation: {role}")
                res = defaultdict(lambda: [])

            # pylint: disable=duplicate-code
--- a/src/axolotl/prompt_strategies/user_defined.py
+++ b/src/axolotl/prompt_strategies/user_defined.py
@@ -1,98 +0,0 @@
-"""
-User Defined prompts with configuration from the YML config
-"""
-
-from dataclasses import dataclass
-from functools import partial
-from typing import Optional, Tuple
-
-from axolotl.prompt_strategies.alpaca_w_system import (
-    InstructionWSystemPromptTokenizingStrategy,
-    SystemDataPrompter,
-)
-
-
-@dataclass
-class UserDefinedDatasetConfig:
-    """
-    dataclass configuration representing a userdefined dataset type
-    """
-
-    system_prompt: str = ""
-    field_system: str = "system"
-    field_instruction: str = "instruction"
-    field_input: str = "input"
-    field_output: str = "output"
-    format: str = "{instruction} {input} "
-    no_input_format: str = "{instruction} "
-    system_format: str = "{system}"
-
-    def __getitem__(self, item):
-        return getattr(self, item)
-
-
-class UserDefinedPromptTokenizationStrategy(InstructionWSystemPromptTokenizingStrategy):
-    """
-    Prompt Tokenization Strategy for user defined prompts
-    """
-
-
-def load(tokenizer, cfg, ds_cfg: Optional[UserDefinedDatasetConfig] = None):
-    if not ds_cfg:
-        raise ValueError("Missing dataset prompt configuration")
-
-    system_prompt = ""
-    if ds_cfg.system_prompt:
-        system_prompt = ds_cfg.system_prompt
-
-    def parse_instruction_fields(
-        field_instruction,
-        field_input,
-        field_output,
-        field_system,
-        system_prompt,
-        prompt,
-    ) -> Tuple[str, str, str, str]:
-        return (
-            prompt[field_instruction],
-            prompt[field_input] if field_input in prompt else "",
-            prompt[field_output] if field_output in prompt else "",
-            prompt[field_system] if field_system in prompt else system_prompt,
-        )
-
-    turn_format = ds_cfg.format
-    turn_no_input_format = ds_cfg.no_input_format
-    system_format = ds_cfg.system_format
-
-    class UserDefinedPrompter(SystemDataPrompter):
-        """
-        Prompter for user defined prompts
-        """
-
-        def match_prompt_style(self):
-            self.turn_format = turn_format
-            self.turn_no_input_format = turn_no_input_format
-            self.system_format = system_format
-
-    prompter = UserDefinedPrompter()
-
-    strat = UserDefinedPromptTokenizationStrategy(
-        prompter,
-        tokenizer,
-        cfg.train_on_inputs,
-        cfg.sequence_len,
-    )
-
-    setattr(
-        strat,
-        "parse_instruction_fields",
-        partial(
-            parse_instruction_fields,
-            ds_cfg.field_instruction,
-            ds_cfg.field_input,
-            ds_cfg.field_output,
-            ds_cfg.field_system,
-            system_prompt,
-        ),
-    )
-    return strat
--- a/src/axolotl/prompt_tokenizers.py
+++ b/src/axolotl/prompt_tokenizers.py
@@ -10,10 +10,8 @@ from transformers import PreTrainedTokenizer

 from axolotl.prompters import IGNORE_TOKEN_ID

-LOG = logging.getLogger("axolotl")
-
 IGNORE_INDEX = -100
-LLAMA_DEFAULT_PAD_TOKEN = "<pad>"  # nosec
+LLAMA_DEFAULT_PAD_TOKEN = "[PAD]"  # nosec
 LLAMA_DEFAULT_EOS_TOKEN = "</s>"  # nosec
 LLAMA_DEFAULT_BOS_TOKEN = "<s>"  # nosec
 LLAMA_DEFAULT_UNK_TOKEN = "<unk>"  # nosec
@@ -48,22 +46,16 @@ class PromptTokenizingStrategy(abc.ABC):

    @functools.lru_cache(maxsize=128)
    def _get_user_token(self):
-        try:
-            id_or_ids = self.tokenizer.convert_tokens_to_ids("<|USER|>")
-            if isinstance(id_or_ids, (int,)):
-                return id_or_ids
-        except KeyError:
-            pass
+        id_or_ids = self.tokenizer.convert_tokens_to_ids("<|USER|>")
+        if isinstance(id_or_ids, (int,)):
+            return id_or_ids
        return False

    @functools.lru_cache(maxsize=128)
    def _get_assistant_token(self):
-        try:
-            id_or_ids = self.tokenizer.convert_tokens_to_ids("<|ASSISTANT|>")
-            if isinstance(id_or_ids, (int,)):
-                return id_or_ids
-        except KeyError:
-            pass
+        id_or_ids = self.tokenizer.convert_tokens_to_ids("<|ASSISTANT|>")
+        if isinstance(id_or_ids, (int,)):
+            return id_or_ids
        return False

    def _tokenize(self, prompt: str, add_eos_token=True, strip_bos_token=False):
@@ -74,22 +66,15 @@ class PromptTokenizingStrategy(abc.ABC):
            padding=False,
            return_tensors=None,
        )
-        if len(result["input_ids"]) == 0:
-            LOG.warning("Tokenizer result is empty. You may want to audit your dataset")
        if (
-            len(result["input_ids"]) > 0
-            and result["input_ids"][-1] != self.tokenizer.eos_token_id
+            result["input_ids"][-1] != self.tokenizer.eos_token_id
            and len(result["input_ids"]) < self.sequence_len
            and add_eos_token
        ):
            result["input_ids"].append(self.tokenizer.eos_token_id)
            result["attention_mask"].append(1)

-        if (
-            len(result["input_ids"]) > 0
-            and result["input_ids"][0] == self.tokenizer.bos_token_id
-            and strip_bos_token
-        ):
+        if result["input_ids"][0] == self.tokenizer.bos_token_id and strip_bos_token:
            result["input_ids"] = result["input_ids"][1:]
            result["attention_mask"] = result["attention_mask"][1:]

@@ -399,7 +384,7 @@ class ShareGPTPromptTokenizingStrategy(PromptTokenizingStrategy):
                        # everything from this is masked out from the labels
                        labels = [IGNORE_TOKEN_ID] * len(res["input_ids"])
                    else:
-                        LOG.warning(f"unhandled role: {part[0]}")
+                        logging.warning(f"unhandled role: {part[0]}")

                # pylint: disable=duplicate-code
                result, current_len = parse_tokenized_to_result(
--- a/src/axolotl/prompters.py
+++ b/src/axolotl/prompters.py
@@ -5,7 +5,6 @@ import logging
 from enum import Enum, auto
 from typing import Generator, List, Optional, Tuple, Union

-LOG = logging.getLogger("axolotl")
 IGNORE_TOKEN_ID = -100


@@ -16,7 +15,6 @@ class PromptStyle(Enum):

    INSTRUCT = "instruct"
    CHAT = "chat"
-    CHATML = "chatml"


 class AlpacaPrompter:
@@ -26,7 +24,6 @@ class AlpacaPrompter:

    system_prompt = "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n"
    system_no_input_prompt = "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n"
-    system_format: str = "{system}"
    turn_format: str
    turn_no_input_format: str
    prompt_style: Optional[PromptStyle] = None
@@ -36,23 +33,14 @@ class AlpacaPrompter:
        self.match_prompt_style()

    def match_prompt_style(self):
-        # pylint: disable=duplicate-code
        if self.prompt_style == PromptStyle.INSTRUCT.value:
            self.turn_format = "### Instruction:\n{instruction}\n\n### Input:\n{input}\n\n### Response:\n"
            self.turn_no_input_format = (
                "### Instruction:\n{instruction}\n\n### Response:\n"
            )
-            self.system_format = "### System:\n{system}\n\n"
        if self.prompt_style == PromptStyle.CHAT.value:
            self.turn_format = "USER: {instruction}\n{input}\nASSISTANT:"
            self.turn_no_input_format = "USER: {instruction}\nASSISTANT:"
-            self.system_format = "SYSTEM: {system}\n"
-        if self.prompt_style == PromptStyle.CHATML.value:
-            self.turn_format = "<|im_start|>user\n{instruction}\n{input}<|im_end|>\n<|im_start|>assistant\n"
-            self.turn_no_input_format = (
-                "<|im_start|>user\n{instruction}<|im_end|>\n<|im_start|>assistant\n"
-            )
-            self.system_format = "<|im_start|>system\n{system}<|im_end|>\n"

    def build_prompt(
        self,
@@ -63,17 +51,13 @@ class AlpacaPrompter:
        # returns the full prompt from instruction and optional input
        # if a label (=response, =output) is provided, it's also appended.
        if input:
-            res = (
-                self.system_format.format(system=self.system_prompt)
-                if self.system_prompt
-                else ""
-            ) + self.turn_format.format(instruction=instruction, input=input)
+            res = self.system_prompt + self.turn_format.format(
+                instruction=instruction, input=input
+            )
        else:
-            res = (
-                self.system_format.format(system=self.system_no_input_prompt)
-                if self.system_prompt
-                else ""
-            ) + self.turn_no_input_format.format(instruction=instruction)
+            res = self.system_no_input_prompt + self.turn_no_input_format.format(
+                instruction=instruction
+            )
        if output:
            res = f"{res}{output}"
        yield res
@@ -257,7 +241,7 @@ class Conversation:
            if message:
                yield (role + ":", " " + message)
            else:
-                LOG.warning(f"role with empty message: {role}")
+                logging.warning(f"role with empty message: {role}")
                yield (role + ":", "")

    def copy(self):
@@ -275,11 +259,6 @@ class Conversation:
        self.messages.append([role, message])


-SHAREGPT_ASSERTION_FAILED_ROLE = (
-    "Role did not alternate between turns (gpt and human). Please check your data."
-)
-
-
 class ShareGPTPrompter:  # pylint: disable=too-few-public-methods
    """
    A prompter that generates prompts for the ShareGPT
@@ -316,9 +295,7 @@ class ShareGPTPrompter:  # pylint: disable=too-few-public-methods
        if len(source) < 2:
            # If there isn't a back and forth conversation, ignore it
            # also happens on the data splitting leaving empty conversations
-            raise IndexError(
-                f"A conversation entry has less than 2 messages :\n{source}"
-            )
+            raise IndexError

        conv = self._conversation.copy()
        roles = {"human": conv.roles[0], "gpt": conv.roles[1]}
@@ -338,7 +315,7 @@ class ShareGPTPrompter:  # pylint: disable=too-few-public-methods
        conv.messages = []
        for j, sentence in enumerate(source):
            role = roles[sentence["from"]]
-            assert role == conv.roles[j % 2], SHAREGPT_ASSERTION_FAILED_ROLE
+            assert role == conv.roles[j % 2]
            conv.append_message(role, sentence["value"])

        for part in conv.get_prompt():
--- a/src/axolotl/train.py
+++ b/src/axolotl/train.py
@@ -1,139 +0,0 @@
-"""Prepare and train a model on a dataset. Can also infer from a model or merge lora"""
-
-import logging
-import os
-import signal
-import sys
-from dataclasses import dataclass
-from pathlib import Path
-from typing import Optional
-
-import torch
-
-# add src to the pythonpath so we don't need to pip install this
-from datasets import Dataset
-from optimum.bettertransformer import BetterTransformer
-
-from axolotl.common.cli import TrainerCliArgs
-from axolotl.logging_config import configure_logging
-from axolotl.utils.dict import DictDefault
-from axolotl.utils.models import load_model, load_tokenizer
-from axolotl.utils.trainer import setup_trainer
-
-project_root = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
-src_dir = os.path.join(project_root, "src")
-sys.path.insert(0, src_dir)
-
-configure_logging()
-LOG = logging.getLogger("axolotl.train")
-
-
-@dataclass
-class TrainDatasetMeta:
-    """
-    dataclass to capture the dataset specific options for training
-    """
-
-    train_dataset: Dataset
-    eval_dataset: Optional[Dataset] = None
-    total_num_steps: Optional[int] = None
-
-
-def train(
-    *,
-    cfg: DictDefault,
-    cli_args: TrainerCliArgs,
-    dataset_meta: TrainDatasetMeta,
-):
-    # load the tokenizer first
-    LOG.info(f"loading tokenizer... {cfg.tokenizer_config or cfg.base_model_config}")
-    tokenizer = load_tokenizer(cfg)
-
-    train_dataset = dataset_meta.train_dataset
-    eval_dataset = dataset_meta.eval_dataset
-    total_num_steps = dataset_meta.total_num_steps
-
-    # Load the model and tokenizer
-    LOG.info("loading model and (optionally) peft_config...")
-    model, peft_config = load_model(cfg, tokenizer, inference=cli_args.inference)
-
-    safe_serialization = cfg.save_safetensors is True
-
-    if cfg.resume_from_checkpoint is None and cfg.auto_resume_from_checkpoints:
-        possible_checkpoints = [
-            str(cp) for cp in Path(cfg.output_dir).glob("checkpoint-*")
-        ]
-        if len(possible_checkpoints) > 0:
-            sorted_paths = sorted(
-                possible_checkpoints,
-                key=lambda path: int(path.split("-")[-1]),
-            )
-            cfg.resume_from_checkpoint = sorted_paths[-1]
-            LOG.info(
-                f"Using Auto-resume functionality to start with checkpoint at {cfg.resume_from_checkpoint}"
-            )
-    resume_from_checkpoint = cfg.resume_from_checkpoint
-
-    trainer = setup_trainer(
-        cfg, train_dataset, eval_dataset, model, tokenizer, total_num_steps
-    )
-
-    model.config.use_cache = False
-
-    if torch.__version__ >= "2" and sys.platform != "win32":
-        LOG.info("Compiling torch model")
-        model = torch.compile(model)
-
-    # go ahead and presave, so we have the adapter config available to inspect
-    if peft_config:
-        LOG.info(f"Pre-saving adapter config to {cfg.output_dir}")
-        peft_config.save_pretrained(cfg.output_dir)
-
-    # In case we want to stop early with ctrl+c, this is a nice to have to save the pretrained model
-    if cfg.local_rank == 0:
-
-        def terminate_handler(_, __, model):
-            if cfg.flash_optimum:
-                model = BetterTransformer.reverse(model)
-            model.save_pretrained(cfg.output_dir, safe_serialization=safe_serialization)
-            sys.exit(0)
-
-        signal.signal(
-            signal.SIGINT, lambda signum, frame: terminate_handler(signum, frame, model)
-        )
-
-    LOG.info("Starting trainer...")
-    if cfg.group_by_length:
-        LOG.info("hang tight... sorting dataset for group_by_length")
-
-    if not Path(cfg.output_dir).is_dir():
-        os.makedirs(cfg.output_dir, exist_ok=True)
-    tokenizer.save_pretrained(cfg.output_dir)
-    if cfg.flash_optimum:
-        with torch.backends.cuda.sdp_kernel(
-            enable_flash=True, enable_math=True, enable_mem_efficient=True
-        ):
-            trainer.train(resume_from_checkpoint=resume_from_checkpoint)
-    else:
-        trainer.train(resume_from_checkpoint=resume_from_checkpoint)
-
-    LOG.info(f"Training Completed!!! Saving pre-trained model to {cfg.output_dir}")
-
-    if cfg.relora_steps:
-        if cfg.adapter == "lora" and not (cfg.load_in_4bit or cfg.load_in_8bit):
-            model = model.merge_and_unload()
-        else:
-            # final model weights have already been saved by `ReLoRACallback.on_train_end`
-            return model, tokenizer
-
-    # TODO do we need this fix? https://huggingface.co/docs/accelerate/usage_guides/fsdp#saving-and-loading
-    # only save on rank 0, otherwise it corrupts output on multi-GPU when multiple processes attempt to write the same file
-    if cfg.fsdp:
-        trainer.save_model(cfg.output_dir)
-    elif cfg.local_rank == 0:
-        if cfg.flash_optimum:
-            model = BetterTransformer.reverse(model)
-
-        model.save_pretrained(cfg.output_dir, safe_serialization=safe_serialization)
-
-    return model, tokenizer
--- a/src/axolotl/utils/bench.py
+++ b/src/axolotl/utils/bench.py
@@ -1,43 +0,0 @@
-"""Benchmarking and measurement utilities"""
-
-import pynvml
-import torch
-
-
-def gpu_memory_usage(device=0):
-    return torch.cuda.memory_allocated(device) / 1024.0**3
-
-
-def gpu_memory_usage_all(device=0):
-    usage = torch.cuda.memory_allocated(device) / 1024.0**3
-    reserved = torch.cuda.memory_reserved(device) / 1024.0**3
-    smi = gpu_memory_usage_smi(device)
-    return usage, reserved - usage, max(0, smi - reserved)
-
-
-def gpu_memory_usage_smi(device=0):
-    if isinstance(device, torch.device):
-        device = device.index
-    if isinstance(device, str) and device.startswith("cuda:"):
-        device = int(device[5:])
-
-    pynvml.nvmlInit()
-    handle = pynvml.nvmlDeviceGetHandleByIndex(device)
-    info = pynvml.nvmlDeviceGetMemoryInfo(handle)
-    return info.used / 1024.0**3
-
-
-def log_gpu_memory_usage(log, msg, device):
-    if not torch.cuda.is_available():
-        return (0, 0, 0)
-
-    usage, cache, misc = gpu_memory_usage_all(device)
-    extras = []
-    if cache > 0:
-        extras.append(f"+{cache:.03f}GB cache")
-    if misc > 0:
-        extras.append(f"+{misc:.03f}GB misc")
-    log.info(
-        f"GPU memory usage {msg}: {usage:.03f}GB ({', '.join(extras)})", stacklevel=2
-    )
-    return usage, cache, misc
--- a/src/axolotl/utils/callbacks.py
+++ b/src/axolotl/utils/callbacks.py
@@ -1,20 +1,8 @@
 """Callbacks for Trainer class"""

-from __future__ import annotations
-
-import logging
 import os
-from typing import TYPE_CHECKING, Dict, List

-import evaluate
-import numpy as np
-import pandas as pd
-import torch
-import torch.distributed as dist
-from accelerate.state import PartialState
-from datasets import load_dataset
 from optimum.bettertransformer import BetterTransformer
-from tqdm import tqdm
 from transformers import (
    TrainerCallback,
    TrainerControl,
@@ -23,20 +11,6 @@ from transformers import (
 )
 from transformers.trainer_utils import PREFIX_CHECKPOINT_DIR, IntervalStrategy

-from axolotl.utils.bench import log_gpu_memory_usage
-from axolotl.utils.distributed import (
-    gather_scalar_from_all_ranks,
-    get_world_size,
-    is_main_process,
-)
-
-if TYPE_CHECKING:
-    from axolotl.utils.trainer import AxolotlTrainingArguments
-
-LOG = logging.getLogger("axolotl.callbacks")
-IGNORE_INDEX = -100
-dist_state = PartialState()
-

 class SavePeftModelCallback(TrainerCallback):  # pylint: disable=too-few-public-methods
    """Callback to save the PEFT adapter"""
@@ -54,9 +28,7 @@ class SavePeftModelCallback(TrainerCallback):  # pylint: disable=too-few-public-
        )

        peft_model_path = os.path.join(checkpoint_folder, "adapter_model")
-        kwargs["model"].save_pretrained(
-            peft_model_path, save_safetensors=args.save_safetensors
-        )
+        kwargs["model"].save_pretrained(peft_model_path)

        return control

@@ -95,221 +67,3 @@ class SaveBetterTransformerModelCallback(
            # the trainer will raise an exception since it can't save a BetterTransformer wrapped model
            control.should_save = False
        return control
-
-
-class GPUStatsCallback(
-    TrainerCallback
-):  # pylint: disable=too-few-public-methods disable=unused-argument
-    """Callback to track GPU utilization"""
-
-    def __init__(self, cfg):
-        self.cfg = cfg
-        self.logged = False
-
-    def on_step_end(
-        self,
-        args: TrainingArguments,
-        state: TrainerState,
-        control: TrainerControl,
-        **kwargs,
-    ):
-        if not self.logged and state.global_step > 1:
-            log_gpu_memory_usage(LOG, "while training", self.cfg.device)
-            self.logged = True
-        return control
-
-
-def bench_eval_callback_factory(trainer, tokenizer):
-    accuracy = evaluate.load("accuracy")
-    abcd_idx = [
-        tokenizer("A", add_special_tokens=False).input_ids[0],
-        tokenizer("B", add_special_tokens=False).input_ids[0],
-        tokenizer("C", add_special_tokens=False).input_ids[0],
-        tokenizer("D", add_special_tokens=False).input_ids[0],
-        tokenizer("E", add_special_tokens=False).input_ids[0],
-        tokenizer("F", add_special_tokens=False).input_ids[0],
-        tokenizer("G", add_special_tokens=False).input_ids[0],
-    ]
-    bench_split = "eval"
-
-    def transform_bench_subject(example):
-        # Split on ':' and trim whitespace
-        parts = example["subject"].split(":")
-        first_part = (
-            parts[0].strip().lower().replace("-", "_")
-        )  # Lowercase the first part
-        second_part = (
-            parts[1].strip().replace("-", "_") if len(parts) > 1 else "all"
-        )  # Replace hyphens with underscores
-
-        # Return the transformed values
-        return {"name": first_part, "subject": second_part}
-
-    if trainer.args.bench_dataset == "mmlu-zs":
-        bench_dataset = load_dataset(
-            "openaccess-ai-collective/mmlu-evals",
-            data_files={
-                "eval": "zero_shot_mmlu_val.json",
-                "test": "zero_shot_mmlu_test.json",
-            },
-        )
-        # bench_dataset = bench_dataset.remove_columns("subject")
-    # MMLU Five-shot (Eval/Test only)
-    elif trainer.args.bench_dataset in ["mmlu", "mmlu-fs"]:
-        bench_dataset = load_dataset(
-            "openaccess-ai-collective/mmlu-evals",
-            data_files={
-                "eval": "five_shot_mmlu_val.json",
-                "test": "five_shot_mmlu_test.json",
-            },
-        )
-        # bench_dataset = bench_dataset.remove_columns('subject')
-    elif "/" in trainer.args.bench_dataset:
-        bench_ds = trainer.args.bench_dataset
-        bench_ds_name = "/".join(bench_ds.split("/", 2)[:2])
-        bench_ds_data_file = "/".join(bench_ds.split("/", 2)[2:])
-        bench_dataset = load_dataset(
-            bench_ds_name,
-            data_files={
-                "eval": bench_ds_data_file,
-            },
-        )
-        bench_dataset["eval"] = bench_dataset["eval"].map(transform_bench_subject)
-    else:
-        raise ValueError(
-            f"unhandled value `{trainer.args.bench_dataset}` for bench_dataset training args"
-        )
-    bench_dataset = bench_dataset[trainer.args.bench_split]
-    if trainer.args.max_bench_samples is not None:
-        bench_dataset = bench_dataset.select(range(trainer.args.max_bench_samples))
-
-    def tokenize_evals(example):
-        source = f"{tokenizer.bos_token}{example['input']}"
-        target = f"{example['output']}{tokenizer.eos_token}"
-
-        tokenized_source = tokenizer(
-            source,
-            max_length=2048,
-            truncation=True,
-            add_special_tokens=False,
-        )
-        tokenized_target = tokenizer(
-            target,
-            max_length=2048,
-            truncation=True,
-            add_special_tokens=False,
-        )
-        input_ids = tokenized_source["input_ids"] + tokenized_target["input_ids"]
-        labels = [IGNORE_INDEX] * len(tokenized_source["input_ids"]) + tokenized_target[
-            "input_ids"
-        ]
-
-        return {
-            "input_ids": input_ids,
-            "labels": labels,
-            "subject": example["subject"],
-        }
-
-    with dist_state.main_process_first():
-        bench_dataset = bench_dataset.map(tokenize_evals)
-        bench_dataset = bench_dataset.filter(lambda x: x["labels"][-2] in abcd_idx)
-
-    class BenchEvalCallback(TrainerCallback):
-        """
-        TrainerCallback that runs the MMLU evals
-        """
-
-        def on_evaluate(
-            self,
-            args: AxolotlTrainingArguments,
-            state: TrainerState,  # pylint: disable=unused-argument
-            control: TrainerControl,  # pylint: disable=unused-argument
-            metrics: Dict[str, float],  # pylint: disable=unused-argument
-            **kwargs,  # pylint: disable=unused-argument
-        ):
-            data_loader = trainer.get_bench_dataloader(
-                bench_dataset.remove_columns(["input", "subject", "output", "name"])
-            )
-            trainer.model.eval()
-            preds, refs = [], []
-            loss_bench = 0
-            for batch in tqdm(data_loader, total=len(data_loader)):
-                (loss, logits, labels) = trainer.prediction_step(
-                    trainer.model,
-                    batch,
-                    prediction_loss_only=False,
-                )
-                # There are two tokens, the output, and eos token.
-                for i, logit in enumerate(logits):
-                    label_non_zero_id = (batch["labels"][i] != IGNORE_INDEX).nonzero()[
-                        0
-                    ][0]
-                    logit_abcd = logit[label_non_zero_id - 1][abcd_idx]
-                    preds.append(torch.argmax(logit_abcd).item())
-                labels = labels[labels != IGNORE_INDEX].view(-1, 2)[:, 0]
-                refs += [
-                    abcd_idx.index(label) if label in abcd_idx else -1
-                    for label in labels.tolist()
-                ]
-                loss_bench += loss.item()
-            # Extract results by subject.
-            bench_name = bench_dataset["name"]
-            bench_names: dict = {s: {"refs": [], "preds": []} for s in set(bench_name)}
-            for s, p, r in zip(bench_name, preds, refs):  # pylint: disable=invalid-name
-                bench_names[s]["preds"].append(p)
-                bench_names[s]["refs"].append(r)
-            dist_state.wait_for_everyone()
-            local_bench_names = bench_names
-            gathered_bench_names: List[Dict] = [{} for _ in range(get_world_size())]
-            # Gather results from all GPUs to GPU 0
-
-            loss_bench_ranks = gather_scalar_from_all_ranks(
-                lambda: loss_bench, get_world_size()
-            )
-            len_data_loader_ranks = gather_scalar_from_all_ranks(
-                lambda: len(data_loader), get_world_size()
-            )
-
-            if not is_main_process():
-                dist.gather_object(local_bench_names, dst=0)
-            else:
-                dist.gather_object(local_bench_names, gathered_bench_names, dst=0)
-                bench_loss = sum(loss_bench_ranks) / sum(len_data_loader_ranks)
-                results = {f"{bench_split}_bench_loss": bench_loss}
-
-                # Combine results from all GPUs
-                combined_bench_names: Dict[str, Dict[str, List]] = {}
-                for bench_name in gathered_bench_names:
-                    for name, data in bench_name.items():
-                        if name not in combined_bench_names:
-                            combined_bench_names[name] = {"refs": [], "preds": []}
-                        combined_bench_names[name]["refs"].extend(data["refs"])
-                        combined_bench_names[name]["preds"].extend(data["preds"])
-
-                bench_scores = []
-                bench_refs = []
-                bench_preds = []
-                for (
-                    bench_name
-                ) in combined_bench_names:  # pylint: disable=consider-using-dict-items
-                    bench_score = accuracy.compute(
-                        references=combined_bench_names[bench_name]["refs"],
-                        predictions=combined_bench_names[bench_name]["preds"],
-                    )["accuracy"]
-                    bench_refs.extend(combined_bench_names[bench_name]["refs"])
-                    bench_preds.extend(combined_bench_names[bench_name]["preds"])
-                    if not pd.isna(bench_score):
-                        results[
-                            f"{bench_split}_bench_accuracy_{bench_name}"
-                        ] = bench_score
-                        bench_scores.append(bench_score)
-                    else:
-                        results[f"{bench_split}_bench_accuracy_{bench_name}"] = 0.0
-                        bench_scores.append(0.0)
-                results[f"{bench_split}_bench_average_accuracy"] = np.mean(bench_scores)
-                results[f"{bench_split}_bench_total_accuracy"] = accuracy.compute(
-                    references=bench_refs, predictions=bench_preds
-                )["accuracy"]
-                trainer.log(results)
-
-    return BenchEvalCallback
--- a/src/axolotl/utils/collators.py
+++ b/src/axolotl/utils/collators.py
@@ -1,121 +0,0 @@
-"""
-DataCollator for axolotl to pad labels and position_ids for packed sequences
-"""
-from dataclasses import dataclass
-from typing import Any, Optional, Union
-
-import numpy as np
-from transformers import PreTrainedTokenizerBase
-from transformers.utils import PaddingStrategy
-
-
-@dataclass
-class DataCollatorForSeq2Seq:
-    """
-    Data collator that will dynamically pad the inputs received, as well as the labels and position_ids
-
-    Args:
-        tokenizer ([`PreTrainedTokenizer`] or [`PreTrainedTokenizerFast`]):
-            The tokenizer used for encoding the data.
-        model ([`PreTrainedModel`]):
-            The model that is being trained. If set and has the *prepare_decoder_input_ids_from_labels*, use it to
-            prepare the *decoder_input_ids*
-
-            This is useful when using *label_smoothing* to avoid calculating loss twice.
-        padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `True`):
-            Select a strategy to pad the returned sequences (according to the model's padding side and padding index)
-            among:
-
-            - `True` or `'longest'` (default): Pad to the longest sequence in the batch (or no padding if only a single
-              sequence is provided).
-            - `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum
-              acceptable input length for the model if that argument is not provided.
-            - `False` or `'do_not_pad'`: No padding (i.e., can output a batch with sequences of different lengths).
-        max_length (`int`, *optional*):
-            Maximum length of the returned list and optionally padding length (see above).
-        pad_to_multiple_of (`int`, *optional*):
-            If set will pad the sequence to a multiple of the provided value.
-
-            This is especially useful to enable the use of Tensor Cores on NVIDIA hardware with compute capability >=
-            7.5 (Volta).
-        label_pad_token_id (`int`, *optional*, defaults to -100):
-            The id to use when padding the labels (-100 will be automatically ignored by PyTorch loss functions).
-        return_tensors (`str`):
-            The type of Tensor to return. Allowable values are "np", "pt" and "tf".
-    """
-
-    tokenizer: PreTrainedTokenizerBase
-    model: Optional[Any] = None
-    padding: Union[bool, str, PaddingStrategy] = True
-    max_length: Optional[int] = None
-    pad_to_multiple_of: Optional[int] = None
-    label_pad_token_id: int = -100
-    position_pad_token_id: int = 0
-    return_tensors: str = "pt"
-
-    def __call__(self, features, return_tensors=None):
-        labels = None
-        if return_tensors is None:
-            return_tensors = self.return_tensors
-
-        for feature_name, pad_token_id in [
-            ("labels", self.label_pad_token_id),
-            ("position_ids", self.position_pad_token_id),
-        ]:
-            feat = (
-                [feature[feature_name] for feature in features]
-                if feature_name in features[0].keys()
-                else None
-            )
-            labels = feat if feat and feature_name == "labels" else labels
-            # We have to pad the labels before calling `tokenizer.pad` as this method won't pad them and needs them of the
-            # same length to return tensors.
-            if feat is not None:
-                max_feature_length = max(len(l) for l in feat)  # noqa: E741
-                if self.pad_to_multiple_of is not None:
-                    max_feature_length = (
-                        (max_feature_length + self.pad_to_multiple_of - 1)
-                        // self.pad_to_multiple_of
-                        * self.pad_to_multiple_of
-                    )
-
-                padding_side = self.tokenizer.padding_side
-                for feature in features:
-                    remainder = [pad_token_id] * (
-                        max_feature_length - len(feature[feature_name])
-                    )
-                    if isinstance(feature[feature_name], list):
-                        feature[feature_name] = (
-                            feature[feature_name] + remainder
-                            if padding_side == "right"
-                            else remainder + feature[feature_name]
-                        )
-                    elif padding_side == "right":
-                        feature[feature_name] = np.concatenate(
-                            [feature[feature_name], remainder]
-                        ).astype(np.int64)
-                    else:
-                        feature[feature_name] = np.concatenate(
-                            [remainder, feature[feature_name]]
-                        ).astype(np.int64)
-
-        features = self.tokenizer.pad(
-            features,
-            padding=self.padding,
-            max_length=self.max_length,
-            pad_to_multiple_of=self.pad_to_multiple_of,
-            return_tensors=return_tensors,
-        )
-
-        # prepare decoder_input_ids
-        if (
-            labels is not None
-            and self.model is not None
-            and hasattr(self.model, "prepare_decoder_input_ids_from_labels")
-        ):
-            decoder_input_ids = self.model.prepare_decoder_input_ids_from_labels(
-                labels=features["labels"]
-            )
-            features["decoder_input_ids"] = decoder_input_ids
-
-        return features
--- a/src/axolotl/utils/config.py
+++ b/src/axolotl/utils/config.py
@@ -1,219 +0,0 @@
-"""Module for working with config dicts"""
-
-import logging
-import os
-
-import torch
-
-from axolotl.utils.bench import log_gpu_memory_usage
-
-LOG = logging.getLogger("axolotl")
-
-
-def choose_device(cfg):
-    def get_device():
-        try:
-            if torch.cuda.is_available():
-                return f"cuda:{cfg.local_rank}"
-
-            if torch.backends.mps.is_available():
-                return "mps"
-
-            raise SystemError("No CUDA/mps device found")
-        except Exception:  # pylint: disable=broad-exception-caught
-            return "cpu"
-
-    cfg.device = get_device()
-    if cfg.device_map != "auto":
-        if cfg.device.startswith("cuda"):
-            cfg.device_map = {"": cfg.local_rank}
-        else:
-            cfg.device_map = {"": cfg.device}
-
-    # in `accelerate launch`, we need to not pass through any device map and let
-    # accelerate figure out which parts of the model to put on which gpu
-    accelerate_vars = [var for var in os.environ if var.startswith("ACCELERATE_USE_")]
-    if accelerate_vars:
-        cfg.device_map = None
-
-
-def normalize_config(cfg):
-    # setup some derived config / hyperparams
-    cfg.gradient_accumulation_steps = cfg.gradient_accumulation_steps or (
-        cfg.batch_size // cfg.micro_batch_size
-    )
-    cfg.batch_size = (
-        cfg.batch_size or cfg.micro_batch_size * cfg.gradient_accumulation_steps
-    )
-    cfg.world_size = int(os.environ.get("WORLD_SIZE", 1))
-    cfg.local_rank = int(os.environ.get("LOCAL_RANK", 0))
-    choose_device(cfg)
-    cfg.ddp = cfg.ddp if cfg.ddp is not None else cfg.world_size != 1
-    if cfg.ddp:
-        cfg.device_map = {"": int(os.environ.get("LOCAL_RANK", 0))}
-        cfg.batch_size = cfg.batch_size * cfg.world_size
-
-    if cfg.device == "mps":
-        cfg.load_in_8bit = False
-        cfg.tf32 = False
-        if cfg.bf16:
-            cfg.fp16 = True
-        cfg.bf16 = False
-    else:
-        torch.backends.cuda.matmul.allow_tf32 = cfg.tf32 or False
-
-    if cfg.bf16 or cfg.bfloat16:
-        cfg.torch_dtype = torch.bfloat16
-    elif cfg.load_in_8bit or cfg.fp16 or cfg.float16:
-        cfg.torch_dtype = torch.float16
-    else:
-        cfg.torch_dtype = torch.float32
-
-    log_gpu_memory_usage(LOG, "baseline", cfg.device)
-
-
-def validate_config(cfg):
-    if cfg.max_packed_sequence_len and cfg.sample_packing:
-        raise ValueError(
-            "please set only one of max_packed_sequence_len (deprecated soon) or sample_packing"
-        )
-    if cfg.max_packed_sequence_len:
-        LOG.warning(
-            str(
-                PendingDeprecationWarning(
-                    "max_packed_sequence_len will be deprecated in favor of sample_packing"
-                )
-            )
-        )
-
-    if cfg.gradient_accumulation_steps and cfg.batch_size:
-        raise ValueError(
-            "please set only one of gradient_accumulation_steps or batch_size"
-        )
-    if cfg.batch_size:
-        LOG.warning(
-            "%s\n%s",
-            "batch_size is not recommended. Please use gradient_accumulation_steps instead.",
-            "To calculate the equivalent gradient_accumulation_steps, divide batch_size / micro_batch_size / number of gpus.",
-        )
-    if cfg.load_4bit:
-        raise ValueError(
-            "cfg.load_4bit parameter has been deprecated and replaced by cfg.gptq"
-        )
-
-    if cfg.adapter == "qlora":
-        if cfg.merge_lora:
-            # can't merge qlora if loaded in 8bit or 4bit
-            if cfg.load_in_8bit:
-                raise ValueError("Can't merge qlora if loaded in 8bit")
-
-            if cfg.gptq:
-                raise ValueError("Can't merge qlora if gptq")
-
-            if cfg.load_in_4bit:
-                raise ValueError("Can't merge qlora if loaded in 4bit")
-
-        else:
-            if cfg.load_in_8bit:
-                raise ValueError("Can't load qlora in 8bit")
-
-            if cfg.gptq:
-                raise ValueError("Can't load qlora if gptq")
-
-            if not cfg.load_in_4bit:
-                raise ValueError("Require cfg.load_in_4bit to be True for qlora")
-
-    if not cfg.load_in_8bit and cfg.adapter == "lora":
-        LOG.warning("We recommend setting `load_in_8bit: true` for LORA finetuning")
-
-    if cfg.relora_steps:
-        if cfg.adapter not in ("lora", "qlora"):
-            raise ValueError("cfg.adapter must be lora or qlora to use ReLoRA")
-
-        if cfg.fsdp:
-            raise ValueError("fsdp not supported with ReLoRA")
-
-        if cfg.deepspeed:
-            raise ValueError("deepspeed not supported with ReLoRA")
-
-        if cfg.lr_scheduler == "one_cycle":
-            raise ValueError("ReLoRA is not compatible with the one_cycle scheduler")
-
-    if cfg.trust_remote_code:
-        LOG.warning(
-            "`trust_remote_code` is set to true. Please make sure that you reviewed the remote code/model."
-        )
-
-    if cfg.push_dataset_to_hub and cfg.hf_use_auth_token is not True:
-        raise ValueError(
-            "Require cfg.hf_use_auth_token to be True for push_dataset_to_hub"
-        )
-
-    if (cfg.base_model and "falcon" in cfg.base_model.lower()) and cfg.fsdp:
-        raise ValueError("FSDP is not supported for falcon models")
-
-    if (
-        cfg.base_model and "mpt" in cfg.base_model.lower()
-    ) and cfg.gradient_checkpointing:
-        raise ValueError("gradient_checkpointing is not supported for MPT models")
-
-    if cfg.flash_optimum is True:
-        if cfg.adapter:
-            LOG.warning("BetterTransformers probably doesn't work with PEFT adapters")
-        if cfg.fp16 or cfg.bf16:
-            raise ValueError("AMP is not supported with BetterTransformer")
-        if cfg.float16 is not True and cfg.bloat16 is not True:
-            LOG.warning(
-                "You should probably set bfloat16 or float16 to true to "
-                "load the model in float16 for BetterTransformers"
-            )
-        if int(torch.__version__.split(".", maxsplit=1)[0]) < 2:
-            LOG.warning("torch>=2.0.0 required")
-            raise ValueError(
-                f"flash_optimum for BetterTransformers may not be used with {torch.__version__}"
-            )
-
-    if cfg.pretraining_dataset and cfg.group_by_length:
-        LOG.warning(
-            "You probably want to disable group_by_length as it will force a streamed dataset to download completely."
-        )
-
-    if any([cfg.adam_beta1, cfg.adam_beta2, cfg.adam_epsilon]) and (
-        not cfg.optimizer or "adamw" not in cfg.optimizer
-    ):
-        LOG.warning("adamw hyperparameters found, but no adamw optimizer set")
-
-    if cfg.push_to_hub_model_id:
-        raise ValueError(
-            "push_to_hub_model_id is deprecated. Please use hub_model_id instead."
-        )
-
-    if cfg.gptq and cfg.model_revision:
-        raise ValueError(
-            "model_revision is not supported for GPTQ models. "
-            + "Please download the model from HuggingFace Hub manually for correct branch, "
-            + "point to its path, and remove model_revision from the config."
-        )
-
-    if cfg.sample_packing and cfg.sdp_attention:
-        # incompatible due to bug w/ accelerate causing 0.0 loss when using llama2
-        raise ValueError(
-            "sample_packing not compatible with sdp_attention. Use flash_attention"
-        )
-
-    if cfg.sample_packing and cfg.xformers_attention:
-        raise ValueError(
-            "sample_packing not compatible with xformers_attention. Use flash_attention"
-        )
-
-    # TODO
-    # MPT 7b
-    # https://github.com/facebookresearch/bitsandbytes/issues/25
-    # no 8bit adaAmw w bf16
-
-    # GPT-NeoX
-    # evals broken when extending context len
-    # File "/root/miniconda3/envs/py3.9/lib/python3.9/site-packages/transformers/models/gpt_neox/modeling_gpt_neox.py", line 162, in forward                        attn_output, attn_weights = self._attn(query, key, value, attention_mask, head_mask)
-    # File "/root/miniconda3/envs/py3.9/lib/python3.9/site-packages/optimum/bettertransformer/models/attention.py", line 74, in gpt2_wrapped_scaled_dot_product
-    # attention_mask = causal_mask + attention_mask
-    # RuntimeError: The size of tensor a (2048) must match the size of tensor b (8132) at non-singleton dimension 3
--- a/src/axolotl/utils/data.py
+++ b/src/axolotl/utils/data.py
@@ -1,20 +1,12 @@
 """Module containing data utilities"""
 import functools
-import hashlib
 import logging
 from hashlib import md5
 from pathlib import Path
-from typing import Tuple, Union
+from typing import List, Tuple, Union

 import torch
-from accelerate.state import PartialState
-from datasets import (
-    Dataset,
-    DatasetDict,
-    concatenate_datasets,
-    load_dataset,
-    load_from_disk,
-)
+from datasets import Dataset, DatasetDict, load_dataset, load_from_disk
 from huggingface_hub import hf_hub_download
 from transformers import PreTrainedTokenizerBase

@@ -42,50 +34,10 @@ from axolotl.prompters import (
    ShareGPTPrompter,
    SummarizeTLDRPrompter,
 )
-from axolotl.utils.dict import DictDefault
-from axolotl.utils.trainer import (
-    calculate_total_num_steps,
-    process_datasets_for_packing,
-)
-
-LOG = logging.getLogger("axolotl")
-DEFAULT_DATASET_PREPARED_PATH = "last_run_prepared"
-state = PartialState()
-
-
-def prepare_dataset(cfg, tokenizer):
-    if not cfg.pretraining_dataset:
-        with state.main_process_first():
-            train_dataset, eval_dataset = load_prepare_datasets(
-                tokenizer, cfg, DEFAULT_DATASET_PREPARED_PATH
-            )
-    else:
-        train_dataset = load_pretraining_dataset(
-            cfg.pretraining_dataset,
-            tokenizer,
-            max_tokens=cfg.sequence_len,
-            seed=cfg.seed or 42,
-        )
-        # https://discuss.huggingface.co/t/how-to-use-huggingface-trainer-streaming-datasets-without-wrapping-it-with-torchdatas-iterablewrapper/25230
-        train_dataset = train_dataset.with_format("torch")
-        eval_dataset = None
-
-    with state.main_process_first():
-        train_dataset, eval_dataset = process_datasets_for_packing(
-            cfg, train_dataset, eval_dataset
-        )
-    if cfg.max_steps:
-        total_num_steps = min(
-            calculate_total_num_steps(cfg, train_dataset, tokenizer), cfg.max_steps
-        )
-        LOG.info(f"Maximum number of steps set at {total_num_steps}")
-    else:
-        total_num_steps = calculate_total_num_steps(cfg, train_dataset, tokenizer)
-    return train_dataset, eval_dataset, total_num_steps


 def load_tokenized_prepared_datasets(
-    tokenizer, cfg, default_dataset_prepared_path
+    split, tokenizer, cfg, default_dataset_prepared_path
 ) -> DatasetDict:
    tokenizer_name = tokenizer.__class__.__name__
    ds_hash = str(
@@ -97,6 +49,8 @@ def load_tokenized_prepared_datasets(
                    sorted([f"{d.path}:{d.type}:{d.shards}" for d in cfg.datasets])
                )
                + "|"
+                + split
+                + "|"
                + tokenizer_name
            ).encode("utf-8")
        ).hexdigest()
@@ -114,44 +68,34 @@ def load_tokenized_prepared_datasets(
                f"{cfg.push_dataset_to_hub}/{ds_hash}",
                use_auth_token=use_auth_token,
            )
-            dataset = dataset["train"]
+            dataset = dataset[split]
    except Exception:  # pylint: disable=broad-except # nosec
        pass

    if dataset:
        ...
    elif any(prepared_ds_path.glob("*")):
-        LOG.info(f"Loading prepared dataset from disk at {prepared_ds_path}...")
+        logging.info(f"Loading prepared dataset from disk at {prepared_ds_path}...")
        dataset = load_from_disk(str(prepared_ds_path))
-        LOG.info("Prepared dataset loaded from disk...")
+        logging.info("Prepared dataset loaded from disk...")
    else:
-        LOG.info(f"Unable to find prepared dataset in {prepared_ds_path}")
-        LOG.info("Loading raw datasets...")
+        logging.info(f"Unable to find prepared dataset in {prepared_ds_path}")
+        logging.info("Loading raw datasets...")

        if cfg.seed:
            seed = cfg.seed
        else:
-            LOG.info("No seed provided, using default seed of 42")
+            logging.info("No seed provided, using default seed of 42")
            seed = 42

        datasets = []
-
-        def for_d_in_datasets(dataset_configs):
-            for dataset in dataset_configs:
-                if dataset.name and isinstance(dataset.name, list):
-                    for name in dataset.name:
-                        yield DictDefault({**dataset, "name": name})
-                else:
-                    yield dataset
-
        # pylint: disable=invalid-name
-        for d in for_d_in_datasets(cfg.datasets):
+        for d in cfg.datasets:
            ds: Union[Dataset, DatasetDict] = None
            ds_from_hub = False
            try:
                load_dataset(
                    d.path,
-                    name=d.name,
                    streaming=True,
                    use_auth_token=use_auth_token,
                )
@@ -160,84 +104,51 @@ def load_tokenized_prepared_datasets(
                pass

            # prefer local dataset, even if hub exists
-            local_path = Path(d.path)
-            if local_path.exists():
-                if local_path.is_dir():
-                    # TODO dirs with arrow or parquet files could be loaded with `load_from_disk`
+            if Path(d.path).exists():
+                ds = load_dataset(
+                    "json",
+                    data_files=d.path,
+                    streaming=False,
+                    split=None,
+                )
+            elif ds_from_hub:
+                if d.data_files:
                    ds = load_dataset(
                        d.path,
-                        name=d.name,
+                        streaming=False,
                        data_files=d.data_files,
-                        streaming=False,
-                        split=None,
-                    )
-                elif local_path.is_file():
-                    ds_type = "json"
-                    if d.ds_type:
-                        ds_type = d.ds_type
-                    elif ".parquet" in d.path:
-                        ds_type = "parquet"
-                    elif ".arrow" in d.path:
-                        ds_type = "arrow"
-                    ds = load_dataset(
-                        ds_type,
-                        name=d.name,
-                        data_files=d.path,
-                        streaming=False,
-                        split=None,
+                        use_auth_token=use_auth_token,
                    )
                else:
-                    raise ValueError(
-                        "unhandled dataset load: local path exists, but is neither a directory or a file"
+                    ds = load_dataset(
+                        d.path,
+                        streaming=False,
+                        use_auth_token=use_auth_token,
                    )
-            elif ds_from_hub:
-                ds = load_dataset(
-                    d.path,
-                    name=d.name,
-                    streaming=False,
-                    data_files=d.data_files,
-                    use_auth_token=use_auth_token,
-                )
            else:
                fp = hf_hub_download(
                    repo_id=d.path,
                    repo_type="dataset",
                    filename=d.data_files,
                )
-                ds = load_dataset(
-                    "json", name=d.name, data_files=fp, streaming=False, split=None
-                )
+                ds = load_dataset("json", data_files=fp, streaming=False, split=None)
            if not ds:
                raise ValueError("unhandled dataset load")
            # support for using a subset of the data
            if d.shards:
-                if "train" in ds:
-                    ds = ds.shuffle(seed=seed)["train"].shard(
+                if split in ds:
+                    ds = ds.shuffle(seed=seed)[split].shard(
                        num_shards=d.shards, index=0
                    )
                else:
                    ds = ds.shuffle(seed=seed).shard(num_shards=d.shards, index=0)
-
-            d_base_type = d_prompt_style = None
            d_type = d.type
-            if isinstance(d_type, str):
-                d_type_split = d_type.split(":")
-                d_base_type = d_type_split[0]
-                d_prompt_style = d_type_split[1] if len(d_type_split) > 1 else None
-            if "train" in ds:
-                ds = ds["train"]
-            if (
-                "input_ids" in ds.features
-                and "attention_mask" in ds.features
-                and "labels" in ds.features
-            ):
-                # dataset is already tokenized, just drop it straight in
-                datasets.append(ds)
-            elif isinstance(d.type, DictDefault):
-                ds_strategy = load("user_defined", tokenizer, cfg, d.type.to_dict())
-                ds_wrapper = TokenizedPromptDataset(ds_strategy, ds)
-                datasets.append(ds_wrapper)
-            elif ds_strategy := load(d.type, tokenizer, cfg, d):
+            d_type_split = d_type.split(":")
+            d_base_type = d_type_split[0]
+            d_prompt_style = d_type_split[1] if len(d_type_split) > 1 else None
+            if split in ds:
+                ds = ds[split]
+            if ds_strategy := load(d.type, tokenizer, cfg):
                ds_wrapper = TokenizedPromptDataset(ds_strategy, ds)
                datasets.append(ds_wrapper)
            elif d_base_type == "alpaca":
@@ -334,21 +245,25 @@ def load_tokenized_prepared_datasets(
                suffix = ""
                if ":load_" in d.type:
                    suffix = f" Did you mean {d.type.replace(':load_', '.load_')}?"
-                LOG.error(f"unhandled prompt tokenization strategy: {d.type}. {suffix}")
+                logging.error(
+                    f"unhandled prompt tokenization strategy: {d.type}. {suffix}"
+                )
                raise ValueError(
                    f"unhandled prompt tokenization strategy: {d.type} {suffix}"
                )
-        LOG.info("merging datasets")
-        dataset = concatenate_datasets(datasets)
+        logging.info("tokenizing, merging, and shuffling master dataset")

-        if len(datasets) > 1:
-            LOG.info("shuffle merged datasets")
-            dataset = dataset.shuffle(seed=seed)
+        samples: List[int] = []
+        for d in datasets:
+            samples = samples + list(d)
+        dataset = Dataset.from_list(samples).shuffle(seed=seed)
        if cfg.local_rank == 0:
-            LOG.info(f"Saving merged prepared dataset to disk... {prepared_ds_path}")
+            logging.info(
+                f"Saving merged prepared dataset to disk... {prepared_ds_path}"
+            )
            dataset.save_to_disk(prepared_ds_path)
            if cfg.push_dataset_to_hub:
-                LOG.info(
+                logging.info(
                    f"Saving merged prepared dataset with push_to_hub... {cfg.push_dataset_to_hub}/{ds_hash}"
                )
                dataset.push_to_hub(
@@ -399,68 +314,90 @@ def load_prepare_datasets(
        use_auth_token = cfg.hf_use_auth_token
        try:
            if cfg.push_dataset_to_hub:
-                LOG.info(
+                logging.info(
                    f"Checking for packed prepared dataset from hub... {cfg.push_dataset_to_hub}/{ds_hash}"
                )
                dataset = load_dataset(
                    f"{cfg.push_dataset_to_hub}/{ds_hash}",
                    use_auth_token=use_auth_token,
                )
-                dataset = dataset["train"]
        except Exception:  # pylint: disable=broad-except # nosec
            pass

        if dataset:
            ...
        elif any(prepared_ds_path.glob("*")):
-            LOG.info(
+            logging.info(
                f"Loading prepared packed dataset from disk at {prepared_ds_path}..."
            )
            dataset = load_from_disk(str(prepared_ds_path))
-            LOG.info("Prepared packed dataset loaded from disk...")
+            logging.info("Prepared packed dataset loaded from disk...")
            if cfg.push_dataset_to_hub:
-                LOG.info(
+                logging.info(
                    f"Saving packed prepared dataset with push_to_hub... {cfg.push_dataset_to_hub}/{ds_hash}"
                )
                dataset.push_to_hub(
                    f"{cfg.push_dataset_to_hub}/{ds_hash}", private=True
                )
        else:
-            dataset = load_tokenized_prepared_datasets(
-                tokenizer, cfg, default_dataset_prepared_path
+            dataset_train = load_tokenized_prepared_datasets(
+                "train", tokenizer, cfg, default_dataset_prepared_path
            )
-
+            dataset_test = load_tokenized_prepared_datasets(
+                "test", tokenizer, cfg, default_dataset_prepared_path
+            )
+            dataset = DatasetDict({"train": dataset_train, "test": dataset_test})
            if cfg.seed:
                dataset = dataset.shuffle(seed=cfg.seed)

-            constant_len_dataset = ConstantLengthDataset(
+            constant_len_dataset_train = ConstantLengthDataset(
                tokenizer,
-                [dataset],
+                [dataset["train"]],
                seq_length=max_packed_sequence_len,
            )
-            LOG.info(f"packing master dataset to len: {cfg.max_packed_sequence_len}")
-            dataset = Dataset.from_list(list(constant_len_dataset))
+            constant_len_dataset_test = ConstantLengthDataset(
+                tokenizer,
+                [dataset["test"]],
+                seq_length=max_packed_sequence_len,
+            )
+            logging.info(
+                f"packing master dataset to len: {cfg.max_packed_sequence_len}"
+            )
+            dataset_train = Dataset.from_list(list(constant_len_dataset_train))
+            dataset_test = Dataset.from_list(list(constant_len_dataset_test))

            # filter out bad data
-            # TODO convert to dataset.filter(...)
-            dataset = Dataset.from_list(
+            dataset_train = Dataset.from_list(
                [
                    d
-                    for d in dataset
-                    if len(d["input_ids"]) <= cfg.sequence_len
+                    for d in dataset_train
+                    if len(d["input_ids"]) < cfg.sequence_len
                    and len(d["input_ids"]) > 0
                    and len(d["input_ids"]) == len(d["attention_mask"])
                    and len(d["input_ids"]) == len(d["labels"])
                ]
            )

+            # filter out bad data
+            dataset_test = Dataset.from_list(
+                [
+                    d
+                    for d in dataset_test
+                    if len(d["input_ids"]) < cfg.sequence_len
+                    and len(d["input_ids"]) > 0
+                    and len(d["input_ids"]) == len(d["attention_mask"])
+                    and len(d["input_ids"]) == len(d["labels"])
+                ]
+            )
+            dataset = DatasetDict({"train": dataset_train, "test": dataset_test})
+
            if cfg.local_rank == 0:
-                LOG.info(
+                logging.info(
                    f"Saving packed prepared dataset to disk... {prepared_ds_path}"
                )
                dataset.save_to_disk(prepared_ds_path)
                if cfg.push_dataset_to_hub:
-                    LOG.info(
+                    logging.info(
                        f"Saving packed prepared dataset with push_to_hub... {cfg.push_dataset_to_hub}/{ds_hash}"
                    )
                    dataset.push_to_hub(
@@ -468,12 +405,16 @@ def load_prepare_datasets(
                        private=True,
                    )
    else:
-        dataset = load_tokenized_prepared_datasets(
-            tokenizer, cfg, default_dataset_prepared_path
+        dataset_train = load_tokenized_prepared_datasets(
+            "train", tokenizer, cfg, default_dataset_prepared_path
        )
+        dataset_test = load_tokenized_prepared_datasets(
+            "test", tokenizer, cfg, default_dataset_prepared_path
+        )
+        dataset = DatasetDict({"train": dataset_train, "test": dataset_test})

    if cfg.dataset_shard_num and cfg.dataset_shard_idx is not None:
-        LOG.info(
+        logging.info(
            f"Using index #{cfg.dataset_shard_idx} of {cfg.dataset_shard_num} shards"
        )
        dataset = dataset.shard(
@@ -482,41 +423,10 @@ def load_prepare_datasets(
        )

    if cfg.val_set_size:
-        # ensure we end up with the same fingerprint by doing rank0 first and being able to cache
-        to_hash_train = (
-            dataset._fingerprint  # pylint: disable=protected-access
-            + "|"
-            + str(cfg.val_set_size)
-            + "|"
-            + "train"
-            + "|"
-            + str(cfg.seed or 42)
-        )
-        to_hash_test = (
-            dataset._fingerprint  # pylint: disable=protected-access
-            + "|"
-            + str(cfg.val_set_size)
-            + "|"
-            + "test"
-            + "|"
-            + str(cfg.seed or 42)
-        )
-        train_fingerprint = hashlib.md5(
-            to_hash_train.encode(), usedforsecurity=False
-        ).hexdigest()
-        test_fingerprint = hashlib.md5(
-            to_hash_test.encode(), usedforsecurity=False
-        ).hexdigest()
-
-        with state.main_process_first():
-            dataset = dataset.train_test_split(
-                test_size=cfg.val_set_size,
-                shuffle=False,
-                seed=cfg.seed or 42,
-                train_new_fingerprint=train_fingerprint,
-                test_new_fingerprint=test_fingerprint,
-            )
-
+        dataset = dataset.train_test_split(test_size=cfg.val_set_size, shuffle=False)
+        train_dataset = dataset["train"]
+        eval_dataset = dataset["test"]
+    elif "train" in dataset:
        train_dataset = dataset["train"]
        eval_dataset = dataset["test"]
    else:
@@ -628,7 +538,7 @@ def encode_pretraining(tokenizer, max_tokens, examples):
        "attention_mask": [seq.tolist() for seq in new_attention_mask],
    }

-    LOG.debug(len(ret["input_ids"]))
+    logging.debug(len(ret["input_ids"]))
    return ret


--- a/src/axolotl/utils/dataloader.py
+++ b/src/axolotl/utils/dataloader.py
@@ -1,300 +0,0 @@
-# pylint: skip-file
-import hashlib
-import itertools
-import logging
-import math
-from typing import Any, Callable, List, Union
-
-import numba
-import numpy as np
-from torch.utils.data import DistributedSampler, Sampler
-
-LOG = logging.getLogger("axolotl.utils.dataloader")
-
-
-@numba.njit
-def ffd_check(a: np.ndarray, c: int, n: int):
-    # First-fit-decreasing bin packing
-    # Check if a[] could fit in n bins with capacity c
-    # https://en.wikipedia.org/wiki/First-fit-decreasing_bin_packing
-
-    a = np.sort(a)[::-1]
-    bins = np.full((n,), c, dtype=a.dtype)
-    for size in a:
-        not_found = True
-        for idx in range(n):
-            if bins[idx] >= size:
-                bins[idx] -= size
-                not_found = False
-                break
-
-        if not_found:
-            return False
-
-    return True
-
-
-@numba.njit
-def ffd_with_result(a: np.ndarray, c: int, start_index: int):
-    # First-fit-decreasing bin packing (with result return)
-
-    indices = np.argsort(a)[::-1]
-    a = a[indices]
-
-    bins: List[Any] = []
-    bins_result: List[Any] = []
-    for a_id, size in enumerate(a):
-        add_new = True
-        for idx in range(len(bins)):
-            if bins[idx] >= size:
-                bins[idx] -= size
-                bins_result[idx].append(indices[a_id] + start_index)
-                add_new = False
-                break
-
-        if add_new:
-            bins.append(c - size)
-            bins_result.append([indices[a_id] + start_index])
-
-    return bins_result, len(a)
-
-
-@numba.njit
-def allocate(
-    lengths: np.ndarray, lengths_cumsum: np.ndarray, rank: int, c: int, n: int
-):
-    """
-    :param lengths: array of lengths of each sample
-    :param lengths_cumsum: cumulative sum of consecutive lengths
-    :param rank: rank for this process
-    :param c: length of tokens per batch
-    :param n: number of ranks
-    :return:
-    """
-    # Dynamic batch allocator, similar to Multifit
-    # https://en.wikipedia.org/wiki/Multifit_algorithm
-    # ~99.5% efficiency on OpenChat training set (12 * 2048 ctx len)
-
-    s = 0
-    start_index = 0
-    result = []
-    result_totseqs = []
-
-    while True:
-        # binary search [left, right)
-        left = 1
-        right = 1 + np.searchsorted(lengths_cumsum[start_index:], s + c * n, "right")
-
-        while right - left > 1:
-            mid = (left + right) // 2
-            if ffd_check(lengths[start_index : start_index + mid], c, n):
-                left = mid
-            else:
-                right = mid
-
-        # use length left
-        batch, tot_seqs = ffd_with_result(
-            lengths[start_index : start_index + left], c, start_index
-        )
-        if len(batch) < n:
-            break
-
-        start_index += left
-        s = lengths_cumsum[start_index - 1]
-
-        # add local rank
-        result.append(batch[rank])
-        # add total seqs for all ranks
-        result_totseqs.append(tot_seqs)
-        # yield batch[rank], tot_seqs, s, len(result) * c * n
-    return result, result_totseqs, s, len(result) * c * n
-
-
-def chunk(iterable, n):
-    """
-    Chunk data into tuples of length n
-    """
-    # batched('ABCDEFG', 3) --> ABC DEF G
-    if n < 1:
-        raise ValueError("n must be at least one")
-    it = iter(iterable)
-    while batch := tuple(itertools.islice(it, n)):
-        yield batch
-
-
-def hash_indices(lst: List[int]) -> str:
-    # Convert the list of integers to a string representation
-    concatenated = ",".join(map(str, lst))
-
-    # Generate the hash
-    sha256 = hashlib.sha256()
-    sha256.update(concatenated.encode())
-
-    return sha256.hexdigest()
-
-
-class MultipackDistributedDataloader:
-    """Unpadded data loading using Multipack.
-    Adapted from https://github.com/imoneoi/openchat/blob/v3_fix_mle_loss/ochat/training_deepspeed/multipack_dataloader.py
-    Approximate (at most ~1.22x) the optimal solution of the identical-machines scheduling problem, which is NP-hard.
-    """
-
-    def __init__(
-        self,
-        dataset: Any,
-        collate_fn: Callable,
-        seq_max_length: int = 2048,
-        batch_size: int = 1,
-        sampler: Union[Sampler, DistributedSampler] = None,
-        packing_efficiency_estimate: float = 1.0,
-        sample_packing_seq_len_multiplier: int = 1,
-        device_count: int = 1,
-    ):
-        # Dataset
-        self.dataset = dataset
-        self.lengths = (
-            dataset.data.column("position_ids")
-            .to_pandas()
-            .apply(lambda x: x[-1] + 1)
-            .values
-        )
-        assert isinstance(self.lengths, np.ndarray)
-        assert batch_size % sample_packing_seq_len_multiplier == 0
-        assert batch_size >= sample_packing_seq_len_multiplier
-        self.sampler = sampler
-        self.batch_size = batch_size
-        self.sample_packing_seq_len_multiplier = sample_packing_seq_len_multiplier
-        self.seq_max_length = seq_max_length
-        self.batch_max_length = batch_size * seq_max_length
-        self.collate_fn = collate_fn
-
-        self.num_replicas = 1
-        self.rank = 0
-
-        # statistics
-        self.eff_total_used = 0
-        self.eff_total_slots = 0
-        self.packing_efficiency_estimate = packing_efficiency_estimate or 1.0
-        self.device_count = device_count
-
-    def generate_batches(self, set_stats=False):
-        LOG.info("generating packed batches")
-        if self.sampler:
-            indices = [idx for idx in self.sampler]
-        else:
-            indices = range(0, len(self.dataset))
-
-        LOG.info(hash_indices(indices))
-        lengths = self.lengths[indices]
-        lengths_cumsum = np.cumsum(lengths)
-
-        batches, totseqs, total_used, total_slots = allocate(
-            lengths=lengths,
-            lengths_cumsum=lengths_cumsum,
-            rank=self.rank,
-            # c=self.batch_max_length,
-            c=self.seq_max_length * self.sample_packing_seq_len_multiplier,
-            n=self.num_replicas,
-        )
-
-        batches = [[indices[b_idx] for b_idx in batch] for batch in batches]
-
-        # statistics
-        if set_stats:
-            self.eff_total_used += total_used
-            self.eff_total_slots += total_slots
-
-        return batches, totseqs
-
-    def __iter__(self):
-        if hasattr(self.sampler, "set_epoch"):
-            new_epoch = self.sampler.epoch + 1
-            self.sampler.set_epoch(new_epoch)
-            LOG.info(f"calling sampler.set_epoch({new_epoch})")
-        all_batches, _ = self.generate_batches(set_stats=True)
-        features = self.dataset.features.keys()
-        len_remaining = self._len_est()
-        for batches in chunk(
-            all_batches, self.batch_size // self.sample_packing_seq_len_multiplier
-        ):
-            chunked_data = []
-            attn_mask_cum_idx = 0
-            for batch in batches:
-                concatenated = {}
-                batched_data = [self.dataset[batch_idx] for batch_idx in batch]
-                for feature in features:
-                    if feature == "attention_mask":
-                        arrays = [
-                            (attn_mask_cum_idx + idx + 1) * np.array(item[feature])
-                            for idx, item in enumerate(batched_data)
-                            if feature in item
-                        ]
-                        attn_mask_cum_idx += len(batched_data)
-                        concatenated[feature] = np.concatenate(arrays)
-                    else:
-                        arrays = [
-                            np.array(item[feature])
-                            for item in batched_data
-                            if feature in item
-                        ]
-                        concatenated[feature] = np.concatenate(arrays)
-                chunked_data.append(concatenated)
-            yield self.collate_fn(chunked_data)
-            len_remaining -= 1
-            if not len_remaining:
-                return
-        # yield a no-op for cases where we don't have any data left to pack
-        for i in range(0, len_remaining):
-            yield self.collate_fn(
-                [
-                    {
-                        "input_ids": [0],
-                        "labels": [-100],
-                        "attention_mask": [True],
-                        "position_ids": [0],
-                    }
-                ]
-            )
-
-    def _len_est(self):
-        lengths_sum = np.sum(self.lengths)
-        lengths_sum_per_device = lengths_sum // self.device_count
-        LOG.info(
-            f"packing_efficiency_estimate: {self.packing_efficiency_estimate} "
-            f"total_num_tokens per device: {lengths_sum_per_device}"
-        )
-
-        # shave off 1% + 1 for dealing with variance in packing from random sampler to sampler
-        return (
-            math.floor(
-                0.99
-                * lengths_sum_per_device
-                / self.packing_efficiency_estimate
-                // self.seq_max_length
-                // self.batch_size
-            )
-            - 1
-        )
-
-    def __len__(self):
-        # this doesn't return the actual length b/c with distributed samplers, not all dataloaders get
-        # the same share of total tokens
-        # if not self.eff_total_used:
-        #     batches, _ = self.generate_batches(set_stats=True)
-        # LOG.info(
-        #     f"packing_efficiency_estimate: {self.packing_efficiency_estimate} "
-        #     f"actual packing efficiency: {self.efficiency()}"
-        # )
-        return max(1, self._len_est())
-
-    def len_w_stats(self):
-        if not self.eff_total_used:
-            batches, _ = self.generate_batches(set_stats=True)
-        LOG.info(
-            f"packing_efficiency_estimate: {self.packing_efficiency_estimate} "
-            f"actual packing efficiency: {self.efficiency()}"
-        )
-        return max(1, self._len_est())
-
-    def efficiency(self):
-        return self.eff_total_used / self.eff_total_slots
--- a/src/axolotl/utils/dict.py
+++ b/src/axolotl/utils/dict.py
@@ -10,6 +10,3 @@ class DictDefault(Dict):

    def __missing__(self, key):
        return None
-
-    def __or__(self, other):
-        return DictDefault(super().__or__(other))
--- a/src/axolotl/utils/distributed.py
+++ b/src/axolotl/utils/distributed.py
@@ -1,76 +0,0 @@
-"""
-utility helpers for distributed checks
-"""
-import torch
-import torch.distributed as dist
-from accelerate import DistributedType
-from accelerate.state import PartialState
-from accelerate.utils import wait_for_everyone
-
-accelerate = None  # pylint: disable=invalid-name
-
-state = PartialState()
-
-
-def is_distributed():
-    """
-    Check if distributed training is initialized.
-    """
-    return state.distributed_type in (
-        DistributedType.MULTI_GPU,
-        DistributedType.MULTI_CPU,
-        DistributedType.DEEPSPEED,
-        DistributedType.FSDP,
-    )
-
-
-def barrier():
-    """
-    Acts as a barrier to wait for all processes. This ensures that all processes
-    reach the barrier before proceeding further.
-    """
-    wait_for_everyone()
-
-
-def is_main_process() -> bool:
-    """
-    Check if the current process is the main process.
-    If not in distributed mode, always return True.
-    """
-    return state.is_main_process
-
-
-def get_world_size() -> int:
-    return state.num_processes
-
-
-def gather_scalar_from_all_ranks(fn, world_size=1):  # pylint: disable=invalid-name
-    """
-    Run a callable 'fn' on all ranks and gather the results on the specified rank.
-
-    Args:
-    - fn (callable): A function that computes the value. This should not have any side effects.
-    - rank (int, optional): The rank that gathers the values. Default is 0.
-    - world_size (int, optional): Total number of processes in the current distributed setup.
-
-    Returns:
-    - A list of computed values from all ranks if on the gathering rank, otherwise None.
-    """
-    value_scalar = fn()
-    value_tensor = torch.tensor(value_scalar, device=dist.get_rank()).float()
-
-    if not state.is_main_process:
-        dist.gather(value_tensor, dst=0)
-    else:
-        gathered_tensors = [torch.zeros_like(value_tensor) for _ in range(world_size)]
-        dist.gather(value_tensor, gather_list=gathered_tensors, dst=0)
-
-        # Convert tensors back to their original type (int or float)
-        gathered_values = []
-        for tensor in gathered_tensors:
-            if tensor == tensor.int():
-                gathered_values.append(int(tensor.item()))
-            else:
-                gathered_values.append(float(tensor.item()))
-        return gathered_values
-    return None
--- a/src/axolotl/utils/models.py
+++ b/src/axolotl/utils/models.py
@@ -5,13 +5,12 @@ import logging
 import math
 import os
 from pathlib import Path
-from typing import Optional, Tuple  # noqa: F401
+from typing import TYPE_CHECKING, Optional, Tuple  # noqa: F401

 import bitsandbytes as bnb
 import torch
 import transformers
 from optimum.bettertransformer import BetterTransformer
-from peft import PeftConfig
 from transformers import (  # noqa: F401
    AutoConfig,
    AutoModelForCausalLM,
@@ -22,60 +21,45 @@ from transformers import (  # noqa: F401
    PreTrainedTokenizerBase,
 )

-from axolotl.prompt_tokenizers import LLAMA_DEFAULT_EOS_TOKEN
-from axolotl.utils.bench import log_gpu_memory_usage
-from axolotl.utils.dict import DictDefault
+from axolotl.prompt_tokenizers import LLAMA_DEFAULT_PAD_TOKEN

-LOG = logging.getLogger("axolotl")
+if TYPE_CHECKING:
+    from peft import PeftConfig  # noqa: F401
+
+    from axolotl.utils.dict import DictDefault  # noqa: F401


-def load_model_config(cfg):
-    model_config_name = cfg.base_model_config or cfg.base_model
-    trust_remote_code: bool = False or cfg.trust_remote_code
-    return AutoConfig.from_pretrained(
-        model_config_name, trust_remote_code=trust_remote_code
-    )
-
-
-def load_tokenizer(cfg):
-    tokenizer_kwargs = {}
+def load_tokenizer(
+    tokenizer_config,
+    tokenizer_type,
+    cfg,
+):
    use_fast = True  # this is the default
-
    if cfg.tokenizer_use_fast is not None:
        use_fast = cfg.tokenizer_use_fast
-    if cfg.tokenizer_legacy is not None:
-        # True is the default w/ https://github.com/huggingface/transformers/pull/25224
-        tokenizer_kwargs["legacy"] = cfg.tokenizer_legacy
+    if tokenizer_type:
+        tokenizer = getattr(transformers, tokenizer_type).from_pretrained(
+            tokenizer_config,
+            trust_remote_code=cfg.trust_remote_code or False,
+            use_fast=use_fast,
+        )
+    else:
+        tokenizer = AutoTokenizer.from_pretrained(
+            tokenizer_config,
+            trust_remote_code=cfg.trust_remote_code or False,
+            use_fast=use_fast,
+        )

-    tokenizer_cls = AutoTokenizer
-    if cfg.tokenizer_type:
-        tokenizer_cls = getattr(transformers, cfg.tokenizer_type)
+    logging.debug(f"EOS: {tokenizer.eos_token_id} / {tokenizer.eos_token}")
+    logging.debug(f"BOS: {tokenizer.bos_token_id} / {tokenizer.bos_token}")
+    logging.debug(f"PAD: {tokenizer.pad_token_id} / {tokenizer.pad_token}")
+    logging.debug(f"UNK: {tokenizer.unk_token_id} / {tokenizer.unk_token}")

-    tokenizer_config = cfg.tokenizer_config or cfg.base_model_config
-    tokenizer = tokenizer_cls.from_pretrained(
-        tokenizer_config,
-        trust_remote_code=cfg.trust_remote_code or False,
-        use_fast=use_fast,
-        **tokenizer_kwargs,
-    )
-
-    if (
-        tokenizer.__class__.__name__
-        in [
-            "LlamaTokenizer",
-            "LlamaTokenizerFast",
-            "CodeLlamaTokenizer",
-        ]
-        and hasattr(tokenizer, "pad_token")
-        and not tokenizer.pad_token
-    ):
-        # set a pad_token, but use eos_token so we don't add a new token
-        tokenizer.pad_token = LLAMA_DEFAULT_EOS_TOKEN
-
-    LOG.debug(f"EOS: {tokenizer.eos_token_id} / {tokenizer.eos_token}")
-    LOG.debug(f"BOS: {tokenizer.bos_token_id} / {tokenizer.bos_token}")
-    LOG.debug(f"PAD: {tokenizer.pad_token_id} / {tokenizer.pad_token}")
-    LOG.debug(f"UNK: {tokenizer.unk_token_id} / {tokenizer.unk_token}")
+    if tokenizer.__class__.__name__ in [
+        "LlamaTokenizer",
+        "LlamaTokenizerFast",
+    ]:
+        tokenizer.pad_token = LLAMA_DEFAULT_PAD_TOKEN

    if tokenizer.__class__.__name__ == "GPTNeoXTokenizerFast":
        tokenizer.add_special_tokens({"pad_token": "[PAD]"})
@@ -91,39 +75,38 @@ def load_tokenizer(cfg):


 def load_model(
-    cfg: DictDefault,
-    tokenizer: PreTrainedTokenizerBase,
-    inference: bool = False,
-) -> Tuple[PreTrainedModel, Optional[PeftConfig]]:
+    base_model, base_model_config, model_type, tokenizer, cfg, adapter="lora"
+):
+    # type: (str, str, str, PreTrainedTokenizerBase, DictDefault, Optional[str]) -> Tuple[PreTrainedModel, Optional[PeftConfig]]
    """
-    Load a model for a given configuration and tokenizer.
+    Load a model from a base model and a model type.
    """
-    base_model = cfg.base_model
-    base_model_config = cfg.base_model_config
-    model_type = cfg.model_type

    # TODO refactor as a kwarg
    load_in_8bit = cfg.load_in_8bit
+    cfg.is_llama_derived_model = "llama" in base_model or (
+        cfg.model_type and "llama" in cfg.model_type.lower()
+    )

    if cfg.is_llama_derived_model and cfg.flash_attention:
-        if cfg.device not in ["mps", "cpu"] and not inference:
-            from axolotl.monkeypatch.llama_attn_hijack_flash import (
-                replace_llama_attn_with_flash_attn,
-            )
+        if cfg.device not in ["mps", "cpu"] and not cfg.inference:
+            from axolotl.flash_attn import replace_llama_attn_with_flash_attn

-            LOG.info("patching with flash attention")
-            replace_llama_attn_with_flash_attn(packed=cfg.sample_packing)
+            logging.info("patching with flash attention")
+            replace_llama_attn_with_flash_attn()
    elif cfg.is_llama_derived_model and cfg.xformers_attention:
        from axolotl.monkeypatch.llama_attn_hijack_xformers import (
            hijack_llama_attention,
        )

-        LOG.info("patching with xformers attention")
+        logging.info("patching with xformers attention")
        hijack_llama_attention()
    elif cfg.is_llama_derived_model and cfg.sdp_attention:
-        from axolotl.monkeypatch.llama_attn_hijack_sdp import hijack_llama_sdp_attention
+        from axolotl.monkeypatch.llama_attn_hijack_xformers import (
+            hijack_llama_sdp_attention,
+        )

-        LOG.info("patching with sdp attention")
+        logging.info("patching with sdp attention")
        hijack_llama_sdp_attention()
    elif cfg.is_llama_derived_model and cfg.landmark_attention:
        from axolotl.monkeypatch.llama_landmark_attn import (
@@ -131,7 +114,7 @@ def load_model(
            patch_llama_with_landmark_attn,
        )

-        LOG.info("patching with landmark attention")
+        logging.info("patching with landmark attention")
        patch_llama_with_landmark_attn()

        # Note: This might overwrite previous additional_special_tokens
@@ -142,19 +125,15 @@ def load_model(
            replace_llama_rope_with_xpos_rope,
        )

-        LOG.info("patching with xpos rope")
+        logging.info("patching with xpos rope")
        replace_llama_rope_with_xpos_rope()

-    if (
-        cfg.is_llama_derived_model
-        and (cfg.max_packed_sequence_len or cfg.sample_packing)
-        and not inference
-    ):
-        from axolotl.monkeypatch.llama_expand_mask import hijack_expand_mask
-
-        LOG.info("patching _expand_mask")
-        hijack_expand_mask()
-
+    if cfg.bf16 or cfg.bfloat16:
+        torch_dtype = torch.bfloat16
+    elif cfg.load_in_8bit or cfg.fp16 or cfg.float16:
+        torch_dtype = torch.float16
+    else:
+        torch_dtype = torch.float32
    try:
        if cfg.gptq:
            from alpaca_lora_4bit.monkeypatch.peft_tuners_lora_monkey_patch import (
@@ -163,30 +142,24 @@ def load_model(

            replace_peft_model_with_int4_lora_model()
    except Exception as err:
-        LOG.exception(err)
+        logging.exception(err)
        raise err

-    if not cfg.gptq and (
-        (cfg.adapter == "lora" and load_in_8bit)
-        or (cfg.adapter == "qlora" and cfg.load_in_4bit)
-    ):
-        try:
-            from peft import prepare_model_for_kbit_training
-        except ImportError:
-            # For backward compatibility
-            from peft import (
-                prepare_model_for_int8_training as prepare_model_for_kbit_training,
-            )
+    try:
+        from peft import prepare_model_for_kbit_training
+    except ImportError:
+        # For backward compatibility
+        from peft import (
+            prepare_model_for_int8_training as prepare_model_for_kbit_training,
+        )

    model_kwargs = {}
-    if cfg.model_revision:
-        model_kwargs["revision"] = cfg.model_revision
    if cfg.adapter == "qlora" and cfg.load_in_4bit:
        model_kwargs["quantization_config"] = BitsAndBytesConfig(
            load_in_4bit=True,
            llm_int8_threshold=6.0,
            llm_int8_has_fp16_weight=False,
-            bnb_4bit_compute_dtype=cfg.torch_dtype,
+            bnb_4bit_compute_dtype=torch_dtype,
            bnb_4bit_use_double_quant=True,
            bnb_4bit_quant_type="nf4",
        )
@@ -212,7 +185,7 @@ def load_model(
                if len(files) > 0:
                    model_path = str(files[0])
                else:
-                    LOG.warning(
+                    logging.warning(
                        "unable to find a cached model file, this will likely fail..."
                    )
                    model_path = str(cache_model_path)
@@ -229,23 +202,17 @@ def load_model(
                else True,
            )
            load_in_8bit = False
-        elif cfg.is_llama_derived_model and not cfg.trust_remote_code:
+        elif cfg.is_llama_derived_model:
            from transformers import LlamaForCausalLM

-            config_kwargs = {}
-            if cfg.rope_scaling:
-                config_kwargs["rope_scaling"] = cfg.rope_scaling
-            config = LlamaConfig.from_pretrained(
-                base_model_config,
-                **config_kwargs,
-            )
+            config = LlamaConfig.from_pretrained(base_model_config)
            model = LlamaForCausalLM.from_pretrained(
                base_model,
                config=config,
-                device_map=cfg.device_map,
                load_in_8bit=cfg.load_in_8bit and cfg.adapter is not None,
                load_in_4bit=cfg.load_in_4bit and cfg.adapter is not None,
-                torch_dtype=cfg.torch_dtype,
+                torch_dtype=torch_dtype,
+                device_map="auto" if cfg.world_size == 1 else cfg.device_map,
                **model_kwargs,
            )
        # elif model_type == "GPTNeoXForCausalLM" and cfg.flash_attention:
@@ -274,13 +241,13 @@ def load_model(
        #         device=cfg.device,
        #     )
        #     model.train() # sets to train instead of eval mode
-        elif model_type and not cfg.trust_remote_code:
+        elif model_type:
            model = getattr(transformers, model_type).from_pretrained(
                base_model,
-                device_map=cfg.device_map,
                load_in_8bit=cfg.load_in_8bit and cfg.adapter is not None,
                load_in_4bit=cfg.load_in_4bit and cfg.adapter is not None,
-                torch_dtype=cfg.torch_dtype,
+                torch_dtype=torch_dtype,
+                device_map=cfg.device_map,
                trust_remote_code=cfg.trust_remote_code or False,
                **model_kwargs,
            )
@@ -297,44 +264,40 @@ def load_model(
                and cfg.sequence_len > config.max_seq_len
            ):
                config.max_seq_len = cfg.sequence_len
-                LOG.warning(f"increasing context length to {cfg.sequence_len}")
+                logging.warning(f"increasing context length to {cfg.sequence_len}")
            elif (
                hasattr(config, "max_sequence_length")
                and config.max_sequence_length
                and cfg.sequence_len > config.max_sequence_length
            ):
                config.max_sequence_length = cfg.sequence_len
-                LOG.warning(f"increasing context length to {cfg.sequence_len}")
+                logging.warning(f"increasing context length to {cfg.sequence_len}")
            model = AutoModelForCausalLM.from_pretrained(
                base_model,
                config=config,
-                device_map=cfg.device_map,
                load_in_8bit=cfg.load_in_8bit and cfg.adapter is not None,
                load_in_4bit=cfg.load_in_4bit and cfg.adapter is not None,
-                torch_dtype=cfg.torch_dtype,
+                torch_dtype=torch_dtype,
+                device_map=cfg.device_map,
                trust_remote_code=cfg.trust_remote_code or False,
                **model_kwargs,
            )
    except Exception as err:  # pylint: disable=broad-exception-caught
-        LOG.error(
+        logging.error(
            "Exception raised attempting to load model, retrying with AutoModelForCausalLM"
        )
-        LOG.exception(err)
+        logging.exception(err)
        model = AutoModelForCausalLM.from_pretrained(
            base_model,
-            device_map=cfg.device_map,
            load_in_8bit=cfg.load_in_8bit and cfg.adapter is not None,
            load_in_4bit=cfg.load_in_4bit and cfg.adapter is not None,
-            torch_dtype=cfg.torch_dtype,
+            torch_dtype=torch_dtype,
+            device_map=cfg.device_map,
            trust_remote_code=cfg.trust_remote_code or False,
            **model_kwargs,
        )

-    embeddings_len = (
-        math.ceil(len(tokenizer) / 32) * 32
-        if cfg.resize_token_embeddings_to_32x
-        else len(tokenizer)
-    )
+    embeddings_len = math.ceil(len(tokenizer) / 32) * 32
    model.resize_token_embeddings(embeddings_len)

    if (
@@ -342,52 +305,28 @@ def load_model(
        and model.config.max_position_embeddings
        and cfg.sequence_len >= model.config.max_position_embeddings
    ):
-        LOG.warning(
+        logging.warning(
            f"increasing model.config.max_position_embeddings to {cfg.sequence_len}"
        )
        model.config.max_position_embeddings = cfg.sequence_len

-    if model.device.type == "cuda":
-        log_gpu_memory_usage(LOG, "after model load", model.device)
-
-    # make sure these are fp32 per Ramesh et al. (2021)
-    for name, module in model.named_modules():
-        if "norm" in name:
-            module.to(torch.float32)
-        if "lm_head" in name or "embed_tokens" in name:
-            if hasattr(module, "weight"):
-                module.to(torch.float32)
-
-    needs_fa2_dtype = cfg.adapter or cfg.fsdp
    if not cfg.gptq and (
        (cfg.adapter == "lora" and load_in_8bit)
        or (cfg.adapter == "qlora" and cfg.load_in_4bit)
    ):
-        LOG.info("converting PEFT model w/ prepare_model_for_kbit_training")
+        logging.info("converting PEFT model w/ prepare_model_for_kbit_training")
        model = prepare_model_for_kbit_training(
            model, use_gradient_checkpointing=cfg.gradient_checkpointing
        )
-        needs_fa2_dtype = True

-    # LlamaRMSNorm layers are in fp32 after kbit_training or full finetune, so we need to
-    # convert them back to fp16/bf16 for flash-attn compatibility.
-    if needs_fa2_dtype or (cfg.flash_attention and cfg.is_llama_derived_model):
-        LOG.info("converting modules to %s for flash attention", cfg.torch_dtype)
-        for name, module in model.named_modules():
-            if "norm" in name:
-                module.to(cfg.torch_dtype)
-            if "lm_head" in name or "embed_tokens" in name:
-                if hasattr(module, "weight"):
-                    module.to(cfg.torch_dtype)
-
-    model, lora_config = load_adapter(model, cfg, cfg.adapter)
+    model, lora_config = load_adapter(model, cfg, adapter)

    if cfg.ddp and not load_in_8bit:
        model.to(f"cuda:{cfg.local_rank}")

    if cfg.gptq:
        # Scales to half
-        LOG.info("Fitting 4bit scales and zeros to half")
+        logging.info("Fitting 4bit scales and zeros to half")
        for _, module in model.named_modules():
            if "Autograd4bitQuantLinear" in str(type(module)) or "Linear4bitLt" in str(
                type(module)
@@ -413,28 +352,23 @@ def load_model(
        if param.requires_grad:
            requires_grad.append(f"{name}: {param.requires_grad}")
    if len(requires_grad) == 0:
-        LOG.warning("there are no parameters that require gradient updates")
+        logging.warning("there are no parameters that require gradient updates")
    model.config.use_cache = False

    if cfg.flash_optimum:
        model = BetterTransformer.transform(model)

-    if cfg.adapter is not None:
-        log_gpu_memory_usage(LOG, "after adapters", model.device)
-
    # TODO resume_from_checkpoint handling
    return model, lora_config


-def load_adapter(model, cfg, adapter, inference=False):
-    # type: (PreTrainedModel, DictDefault, Optional[str], bool) -> Tuple[PreTrainedModel, Optional[PeftConfig]]
+def load_adapter(model, cfg, adapter):
+    # type: (PreTrainedModel, DictDefault, Optional[str]) -> Tuple[PreTrainedModel, Optional[PeftConfig]]

    if adapter is None:
        return model, None
-    if hasattr(model, "enable_input_require_grads"):
-        model.enable_input_require_grads()
    if adapter in ["lora", "qlora"]:
-        return load_lora(model, cfg, inference=inference)
+        return load_lora(model, cfg)
    if adapter == "llama-adapter":
        return load_llama_adapter(model, cfg)

@@ -452,7 +386,7 @@ def load_llama_adapter(model, cfg):
    )

    if cfg.lora_model_dir:
-        LOG.debug("Loading pretained PEFT - llama_adapter")
+        logging.info("Loading pretained LORA")
        model = PeftModel.from_pretrained(
            model,
            cfg.lora_model_dir,
@@ -466,8 +400,12 @@ def load_llama_adapter(model, cfg):
    return model, peft_config


-def find_all_linear_names(model):
-    cls = (bnb.nn.Linear4bit, bnb.nn.Linear8bitLt, torch.nn.Linear)
+def find_all_linear_names(bits, model):
+    cls = (
+        bnb.nn.Linear4bit
+        if bits == 4
+        else (bnb.nn.Linear8bitLt if bits == 8 else torch.nn.Linear)
+    )
    lora_module_names = set()
    for name, module in model.named_modules():
        if isinstance(module, cls):
@@ -480,16 +418,22 @@ def find_all_linear_names(model):
    return list(lora_module_names)


-def load_lora(model, cfg, inference=False):
-    # type: (PreTrainedModel, DictDefault, bool) -> Tuple[PreTrainedModel, Optional[PeftConfig]]
+def load_lora(model, cfg):
+    # type: (PreTrainedModel, DictDefault) -> Tuple[PreTrainedModel, Optional[PeftConfig]]

    from peft import LoraConfig, PeftModel, get_peft_model

    lora_target_modules = list(cfg.lora_target_modules or [])

    if cfg.lora_target_linear:
-        linear_names = find_all_linear_names(model)
-        LOG.info(f"found linear modules: {repr(linear_names)}")
+        bits = None
+        if cfg.load_in_4bit:
+            bits = 4
+        elif cfg.load_in_8bit:
+            bits = 8
+
+        linear_names = find_all_linear_names(bits, model)
+        logging.info(f"found linear modules: {repr(linear_names)}")
        lora_target_modules = list(set(lora_target_modules + linear_names))

    lora_config = LoraConfig(
@@ -504,11 +448,10 @@ def load_lora(model, cfg, inference=False):
    )

    if cfg.lora_model_dir:
-        LOG.debug("Loading pretained PEFT - LoRA")
        model = PeftModel.from_pretrained(
            model,
            cfg.lora_model_dir,
-            is_trainable=(not inference),
+            is_trainable=not cfg.inference,
        )
    else:
        model = get_peft_model(model, lora_config)
--- a/src/axolotl/utils/schedulers.py
+++ b/src/axolotl/utils/schedulers.py
@@ -1,9 +1,6 @@
 """Module for custom LRScheduler class"""
-import math
-from functools import partial

-from torch.optim import Optimizer
-from torch.optim.lr_scheduler import LambdaLR, LRScheduler
+from torch.optim.lr_scheduler import LRScheduler


 class InterpolatingLogScheduler(LRScheduler):
@@ -45,58 +42,3 @@ class InterpolatingLogScheduler(LRScheduler):
            lrs = [self.max_lr for base_lr in self.base_lrs]

        return lrs
-
-
-def _get_cosine_schedule_with_quadratic_warmup_lr_lambda(
-    current_step: int,
-    *,
-    num_warmup_steps: int,
-    num_training_steps: int,
-    num_cycles: float
-):
-    if current_step < num_warmup_steps:
-        return (float(current_step) / float(max(1, num_warmup_steps))) ** 2
-    progress = float(current_step - num_warmup_steps) / float(
-        max(1, num_training_steps - num_warmup_steps)
-    )
-    return max(
-        0.0, 0.5 * (1.0 + math.cos(math.pi * float(num_cycles) * 2.0 * progress))
-    )
-
-
-def get_cosine_schedule_with_quadratic_warmup(
-    optimizer: Optimizer,
-    num_warmup_steps: int,
-    num_training_steps: int,
-    num_cycles: float = 0.5,
-    last_epoch: int = -1,
-):
-    """
-    Create a schedule with a learning rate that decreases following the values of the cosine function between the
-    initial lr set in the optimizer to 0, after a warmup period during which it increases linearly between 0 and the
-    initial lr set in the optimizer.
-
-    Args:
-        optimizer ([`~torch.optim.Optimizer`]):
-            The optimizer for which to schedule the learning rate.
-        num_warmup_steps (`int`):
-            The number of steps for the warmup phase.
-        num_training_steps (`int`):
-            The total number of training steps.
-        num_cycles (`float`, *optional*, defaults to 0.5):
-            The number of waves in the cosine schedule (the defaults is to just decrease from the max value to 0
-            following a half-cosine).
-        last_epoch (`int`, *optional*, defaults to -1):
-            The index of the last epoch when resuming training.
-
-    Return:
-        `torch.optim.lr_scheduler.LambdaLR` with the appropriate schedule.
-    """
-
-    lr_lambda = partial(
-        _get_cosine_schedule_with_quadratic_warmup_lr_lambda,
-        num_warmup_steps=num_warmup_steps,
-        num_training_steps=num_training_steps,
-        num_cycles=num_cycles,
-    )
-    return LambdaLR(optimizer, lr_lambda, last_epoch)
--- a/src/axolotl/utils/tokenization.py
+++ b/src/axolotl/utils/tokenization.py
@@ -5,16 +5,14 @@ import logging

 from termcolor import colored

-LOG = logging.getLogger("axolotl")

-
-def check_dataset_labels(dataset, tokenizer, num_examples=5, text_only=False):
+def check_dataset_labels(dataset, tokenizer):
    # the dataset is already shuffled, so let's just check the first 5 elements
-    for idx in range(num_examples):
-        check_example_labels(dataset[idx], tokenizer, text_only=text_only)
+    for idx in range(5):
+        check_example_labels(dataset[idx], tokenizer)


-def check_example_labels(example, tokenizer, text_only=False):
+def check_example_labels(example, tokenizer):
    # Get the input_ids, labels, and attention_mask from the dataset
    input_ids = example["input_ids"]
    labels = example["labels"]
@@ -29,14 +27,12 @@ def check_example_labels(example, tokenizer, text_only=False):
        decoded_input_token = tokenizer.decode(input_id)
        # Choose the color based on whether the label has the ignore value or not
        color = "red" if label_id == -100 else ("yellow" if label_id == 0 else "green")
-        colored_token = colored(decoded_input_token, color) + (
-            not text_only
-            and colored(f"({label_id}, {mask}, {input_id})", "white")
-            or ""
+        colored_token = colored(decoded_input_token, color) + colored(
+            f"({label_id}, {mask}, {input_id})", "white"
        )
        colored_tokens.append(colored_token)

-    LOG.info(" ".join(colored_tokens))
-    LOG.info("\n\n\n")
+    logging.info(" ".join(colored_tokens))
+    logging.info("\n\n\n")

    return " ".join(colored_tokens)
--- a/src/axolotl/utils/trainer.py
+++ b/src/axolotl/utils/trainer.py
@@ -1,299 +1,29 @@
 """Module containing the Trainer class and related functions"""
+
 import importlib
 import logging
 import math
 import os
 import sys
-from contextlib import contextmanager
-from dataclasses import dataclass, field
-from functools import partial
 from pathlib import Path
-from typing import Optional, Union
+from typing import Optional

-import numpy as np
+import bitsandbytes as bnb
 import torch.cuda
 import transformers
-from datasets import Dataset, set_caching_enabled
+from torch import nn
 from torch.optim.lr_scheduler import OneCycleLR
-from torch.utils.data import (
-    DataLoader,
-    DistributedSampler,
-    RandomSampler,
-    SequentialSampler,
-)
-from transformers import EarlyStoppingCallback, Trainer, TrainingArguments
-from transformers.trainer_pt_utils import SequentialDistributedSampler
+from transformers import EarlyStoppingCallback, Trainer
+from transformers.trainer_pt_utils import get_parameter_names

-from axolotl.monkeypatch.relora import ReLoRACallback, ReLoRAScheduler
 from axolotl.utils.callbacks import (
-    GPUStatsCallback,
    SaveBetterTransformerModelCallback,
    SavePeftModelCallback,
-    bench_eval_callback_factory,
 )
-from axolotl.utils.collators import DataCollatorForSeq2Seq
-from axolotl.utils.dataloader import MultipackDistributedDataloader
-from axolotl.utils.schedulers import get_cosine_schedule_with_quadratic_warmup
-
-LOG = logging.getLogger("axolotl")
+from axolotl.utils.schedulers import InterpolatingLogScheduler


-@torch.jit.script
-def weighted_cross_entropy(
-    logits: torch.Tensor, labels: torch.Tensor, weights: torch.Tensor
-):
-    # Flatten the logits, labels, and weights tensors
-    logits = logits.view(
-        -1, logits.size(-1)
-    )  # logits becomes of shape [batch_size*sequence_length, vocab_size]
-    labels = labels.view(-1)  # labels becomes of shape [batch_size*sequence_length]
-    weights = weights.view(-1)  # weights becomes of shape [batch_size*sequence_length]
-
-    # Compute the unweighted cross entropy loss
-    losses = torch.nn.functional.cross_entropy(logits, labels, reduction="none")
-
-    # Apply the weights to the losses and compute their sum
-    return (weights * losses).sum()
-
-
-@torch.jit.script
-def create_weighted_mask(labels: torch.Tensor):
-    # Check if the tensor is 2D. If not, unsqueeze it to make it 2D
-    if len(labels.shape) == 1:
-        labels = labels.unsqueeze(0)
-
-    weights = torch.zeros_like(labels).float()
-    for i in range(labels.shape[0]):
-        mask = labels[i] != -100
-
-        # Create a tensor to track group ids
-        group_ids = torch.zeros_like(labels[i]).int()
-        curr_group_id = 0
-
-        for j in range(1, len(labels[i])):
-            if mask[j] and not mask[j - 1]:  # switch from masked to unmasked label
-                curr_group_id += 1  # start new group
-            group_ids[j] = (
-                curr_group_id if mask[j] else 0
-            )  # assign group id if unmasked label
-
-        # Count only unmasked labels in each group
-        group_counts = torch.bincount(group_ids[mask])
-
-        mask_weights = torch.zeros_like(labels[i]).float()
-        mask_weights[mask] = 1.0 / group_counts[group_ids[mask]]
-
-        weights[i] = mask_weights
-
-    return weights.squeeze()  # squeeze the output to match the input dimension
-
-
-def trainer_weighted_loss(model_output, labels, shift_labels=True):
-    logits = (
-        model_output["logits"] if isinstance(model_output, dict) else model_output[0]
-    )
-    if shift_labels:
-        logits = logits[..., :-1, :].contiguous()
-        labels = labels[..., 1:].contiguous()
-
-    weights = create_weighted_mask(labels)
-    return weighted_cross_entropy(logits, labels, weights)
-
-
-@dataclass
-class AxolotlTrainingArguments(TrainingArguments):
-    """
-    Extend the base TrainingArguments for axolotl helpers
-    """
-
-    lr_quadratic_warmup: bool = field(
-        default=False,
-        metadata={"help": "Use quadratic warmup for cosine scheduling."},
-    )
-    sample_packing: bool = field(
-        default=False,
-        metadata={"help": "Use sample packing for efficient training."},
-    )
-    sample_packing_efficiency: float = field(
-        default=1.0,
-        metadata={"help": "Sample packing efficiency for calculating batch length."},
-    )
-    max_seq_length: int = field(
-        default=2048,
-        metadata={"help": "The maximum sequence length the model can handle"},
-    )
-    sample_packing_seq_len_multiplier: int = field(
-        default=1,
-        metadata={"help": "the multiplier for the max len for packed sequences"},
-    )
-    relora_steps: Optional[int] = field(
-        default=None,
-        metadata={"help": "how often to reset for ReLoRA"},
-    )
-    relora_warmup_steps: Optional[int] = field(
-        default=None,
-        metadata={"help": "how many warmup steps to take after reset for ReLoRA"},
-    )
-    bench_split: Optional[str] = field(
-        default="eval", metadata={"help": "The benchmark split to run on"}
-    )
-    bench_dataset: Optional[str] = field(
-        default="pharaouk/dharma-1/dharma_1_mini.json",
-        metadata={
-            "help": "Benchmark dataset to use: options are `mmlu-zs`, `mmlu-fs`, or the full path to the dataset file"
-        },
-    )
-    do_bench_eval: Optional[bool] = field(
-        default=False, metadata={"help": "Whether to run the Benchmark evaluation."}
-    )
-    max_bench_samples: Optional[int] = field(
-        default=None,
-        metadata={
-            "help": "If set, only evaluates on `max_bench_samples` of the benchmark dataset."
-        },
-    )
-    bench_source_max_len: int = field(
-        default=2048, metadata={"help": "Maximum source sequence length for bench."}
-    )
-
-
-class AxolotlTrainer(Trainer):
-    """
-    Extend the base Trainer for axolotl helpers
-    """
-
-    args = None  # type: AxolotlTrainingArguments
-
-    def __init__(self, *args, bench_data_collator=None, **kwargs):
-        self.bench_data_collator = bench_data_collator
-        super().__init__(*args, **kwargs)
-
-    def create_scheduler(
-        self, num_training_steps: int, optimizer: torch.optim.Optimizer = None
-    ):
-        """
-        Setup the scheduler. The optimizer of the trainer must have been set up either before this method is called or
-        passed as an argument.
-
-        Args:
-            num_training_steps (int): The number of training steps to do.
-            optimizer (torch.optim.Optimizer): The training optimizer
-        """
-
-        # fmt: off
-        if self.lr_scheduler is None:  # type: ignore  # pylint: disable=access-member-before-definition
-            # fmt: on
-            if (
-                self.args.lr_scheduler_type == "cosine"
-                and self.args.lr_quadratic_warmup is True
-            ):
-                self.lr_scheduler = get_cosine_schedule_with_quadratic_warmup(  # pylint: disable=attribute-defined-outside-init
-                    optimizer,
-                    num_warmup_steps=self.args.get_warmup_steps(num_training_steps),
-                    num_training_steps=num_training_steps,
-                )
-            else:
-                return super().create_scheduler(num_training_steps, optimizer)
-        return self.lr_scheduler
-
-    def _get_train_sampler(self) -> Optional[torch.utils.data.Sampler]:
-        if self.args.world_size > 1 and self.args.sample_packing:
-            return DistributedSampler(
-                self.train_dataset,
-                num_replicas=self.args.world_size,
-                rank=self.args.process_index,
-                seed=self.args.seed,
-            )
-        return super()._get_train_sampler()
-
-    def _get_eval_sampler(
-        self, eval_dataset: Dataset
-    ) -> Optional[torch.utils.data.Sampler]:
-        if self.args.world_size > 1 and self.args.sample_packing:
-            return SequentialDistributedSampler(
-                eval_dataset,
-                num_replicas=self.args.world_size,
-                rank=self.args.process_index,
-                batch_size=self.args.per_device_eval_batch_size,
-            )
-        return super()._get_eval_sampler(eval_dataset)
-
-    def get_train_dataloader(self) -> Union[DataLoader, MultipackDistributedDataloader]:
-        if self.args.sample_packing:
-            train_sampler = self._get_train_sampler()
-            return self.accelerator.prepare(
-                MultipackDistributedDataloader(
-                    self.train_dataset,
-                    batch_size=self._train_batch_size,
-                    seq_max_length=self.args.max_seq_length,
-                    collate_fn=self.data_collator,
-                    sampler=train_sampler,
-                    packing_efficiency_estimate=self.args.sample_packing_efficiency,
-                    sample_packing_seq_len_multiplier=self.args.sample_packing_seq_len_multiplier,
-                    device_count=int(os.environ.get("WORLD_SIZE", 1)),
-                )
-            )
-        return super().get_train_dataloader()
-
-    def get_eval_dataloader(
-        self, eval_dataset: Optional[Dataset] = None
-    ) -> Union[DataLoader, MultipackDistributedDataloader]:
-        if self.args.sample_packing:
-            eval_dataset = (
-                eval_dataset if eval_dataset is not None else self.eval_dataset
-            )
-
-            eval_sampler = self._get_eval_sampler(eval_dataset)
-            return self.accelerator.prepare(
-                MultipackDistributedDataloader(
-                    eval_dataset,
-                    batch_size=self.args.eval_batch_size,
-                    seq_max_length=self.args.max_seq_length,
-                    collate_fn=self.data_collator,
-                    sampler=eval_sampler,
-                    packing_efficiency_estimate=self.args.sample_packing_efficiency,
-                    sample_packing_seq_len_multiplier=self.args.eval_batch_size,
-                    device_count=int(os.environ.get("WORLD_SIZE", 1)),
-                )
-            )
-        return super().get_eval_dataloader(eval_dataset)
-
-    def _get_bench_sampler(
-        self, bench_dataset: Dataset
-    ) -> Optional[torch.utils.data.Sampler]:
-        if self.args.world_size <= 1:
-            return SequentialSampler(bench_dataset)
-        return None
-
-    def get_bench_dataloader(
-        self,
-        bench_dataset: Dataset,
-    ) -> Union[DataLoader, MultipackDistributedDataloader]:
-        dataloader_params = {
-            "batch_size": self.args.eval_batch_size,
-            "collate_fn": self.bench_data_collator,
-            "num_workers": self.args.dataloader_num_workers,
-            "pin_memory": self.args.dataloader_pin_memory,
-        }
-
-        if not isinstance(bench_dataset, torch.utils.data.IterableDataset):
-            dataloader_params["sampler"] = self._get_bench_sampler(bench_dataset)
-            dataloader_params["drop_last"] = self.args.dataloader_drop_last
-
-        return DataLoader(bench_dataset, **dataloader_params)
-        # return self.accelerator.prepare(DataLoader(bench_dataset, **dataloader_params))
-
-    def compute_loss(self, model, inputs, return_outputs=False):
-        # use one's weighted cross entropy loss calc
-        # if self.args.sample_packing:
-        #     labels = inputs.pop("labels")
-        #     outputs = model(**inputs)
-        #     loss = trainer_weighted_loss(outputs, labels, shift_labels=True)
-        #     return (loss, outputs) if return_outputs else loss
-        return super().compute_loss(model, inputs, return_outputs=return_outputs)
-
-
-class OneCycleLRSchedulerTrainer(AxolotlTrainer):
+class OneCycleLRSchedulerTrainer(Trainer):
    """
    Trainer subclass that uses the OneCycleLR scheduler
    """
@@ -322,173 +52,10 @@ class OneCycleLRSchedulerTrainer(AxolotlTrainer):
        return self.lr_scheduler


-class ReLoRATrainer(AxolotlTrainer):
-    """
-    Trainer subclass that uses the OneCycleLR scheduler
-    """
-
-    def __init__(self, *args, **kwargs):
-        super().__init__(*args, **kwargs)
-        self.lr_scheduler = None
-
-    def create_scheduler(
-        self,
-        num_training_steps: int,
-        optimizer: Optional[torch.optim.Optimizer] = None,
-    ):
-        optimizer = self.optimizer if optimizer is None else optimizer
-        lr_scheduler = super().create_scheduler(num_training_steps, optimizer)
-
-        if self.args.relora_steps:
-            warmup_steps = (
-                self.args.relora_warmup_steps if self.args.relora_warmup_steps else 10
-            )
-            self.lr_scheduler = ReLoRAScheduler(
-                optimizer,
-                lr_scheduler,
-                self.args.relora_steps,
-                warmup_steps,
-            )
-        else:
-            self.lr_scheduler = lr_scheduler
-
-        return self.lr_scheduler
-
-
-def add_position_ids(sample):
-    sample["position_ids"] = torch.arange(len(sample["input_ids"]))
-    return sample
-
-
-def drop_long_seq(sample, sequence_len=2048):
-    return len(sample["input_ids"]) <= sequence_len and len(sample["input_ids"]) > 0
-
-
-@contextmanager
-def disable_datasets_caching():
-    try:
-        set_caching_enabled(False)
-        yield
-    finally:
-        set_caching_enabled(True)
-
-
-def process_datasets_for_packing(cfg, train_dataset, eval_dataset):
-    drop_long = partial(drop_long_seq, sequence_len=cfg.sequence_len)
-    train_dataset = train_dataset.filter(drop_long, num_proc=os.cpu_count())
-    if eval_dataset:
-        eval_dataset = eval_dataset.filter(drop_long, num_proc=os.cpu_count())
-
-    if cfg.sample_packing:
-        train_dataset = train_dataset.map(add_position_ids, num_proc=os.cpu_count())
-        if eval_dataset:
-            eval_dataset = eval_dataset.map(add_position_ids, num_proc=os.cpu_count())
-    return train_dataset, eval_dataset
-
-
-def calculate_total_num_steps(cfg, train_dataset, tokenizer):
-    if cfg.sample_packing:
-        # we have to drop anything longer then sequence len otherwise
-        # flash attention with position ids fails
-        if not cfg.total_num_tokens:
-            LOG.info("calculating total_num_tokens")
-            total_num_tokens = np.sum(
-                train_dataset.data.column("input_ids")
-                .to_pandas()
-                .apply(lambda x: len(x))  # pylint: disable=unnecessary-lambda
-                .values
-            )
-            LOG.info(f"📝 UPDATE CONFIG WITH: `total_num_tokens: {total_num_tokens}`")
-            cfg.total_num_tokens = total_num_tokens
-
-        if not cfg.total_supervised_tokens:
-            total_supervised_tokens = (
-                train_dataset.data.column("labels")
-                .to_pandas()
-                .apply(lambda x: np.sum(np.array(x) != -100))
-                .sum()
-            )
-            LOG.info(f"`total_supervised_tokens: {total_supervised_tokens}`")
-            cfg.total_supervised_tokens = total_supervised_tokens
-
-        if cfg.sample_packing_eff_est:
-            total_num_steps = (
-                # match count to len est in dataloader
-                (
-                    math.floor(
-                        0.99
-                        * cfg.total_num_tokens
-                        / cfg.sample_packing_eff_est
-                        / cfg.sequence_len
-                        // cfg.batch_size
-                        // int(os.environ.get("WORLD_SIZE", 1))
-                    )
-                    - 1
-                )
-                * cfg.num_epochs
-            )
-            LOG.info(
-                f"total_num_tokens: {cfg.total_num_tokens}, total_num_steps: {total_num_steps}"
-            )
-        else:
-            sampler = RandomSampler(train_dataset)
-            data_loader = MultipackDistributedDataloader(
-                train_dataset,
-                batch_size=cfg.micro_batch_size,
-                seq_max_length=cfg.max_packed_sequence_len or cfg.sequence_len,
-                collate_fn=DataCollatorForSeq2Seq(
-                    tokenizer,
-                    return_tensors="pt",
-                    padding="longest",
-                ),
-                sampler=sampler,
-                packing_efficiency_estimate=cfg.sample_packing_eff_est,
-                sample_packing_seq_len_multiplier=cfg.micro_batch_size,
-                device_count=int(os.environ.get("WORLD_SIZE", 1)),
-            )
-            data_loader_len = data_loader.len_w_stats()
-            actual_eff = data_loader.efficiency()
-            LOG.info(f"data_loader_len: {data_loader_len}")
-            total_num_steps = int(
-                math.floor(
-                    data_loader_len
-                    * cfg.micro_batch_size
-                    * cfg.num_epochs
-                    // cfg.batch_size
-                )
-            )
-            LOG.info(
-                f"📝 UPDATE CONFIG WITH: `sample_packing_eff_est: {math.ceil(actual_eff * 100.0) / 100.0}`"
-            )
-            cfg.sample_packing_eff_est = math.ceil(actual_eff * 100.0) / 100.0
-    else:
-        total_num_steps = int(
-            math.ceil(len(train_dataset) * cfg.num_epochs / cfg.batch_size)
-        )
-    LOG.info(f"total_num_steps: {total_num_steps}")
-    return total_num_steps
-
-
-def setup_fsdp_envs(cfg):
-    os.environ["ACCELERATE_USE_FSDP"] = "true"
-    if cfg.fsdp_config.fsdp_offload_params:
-        os.environ["FSDP_OFFLOAD_PARAMS"] = "true"
-    if cfg.fsdp_config.fsdp_sync_module_states:
-        os.environ["FSDP_SYNC_MODULE_STATES"] = "true"
-    if cfg.fsdp_config.fsdp_state_dict_type:
-        os.environ["FSDP_STATE_DICT_TYPE"] = cfg.fsdp_config.fsdp_state_dict_type
-    if cfg.fsdp_config.fsdp_transformer_layer_cls_to_wrap:
-        os.environ[
-            "FSDP_TRANSFORMER_CLS_TO_WRAP"
-        ] = cfg.fsdp_config.fsdp_transformer_layer_cls_to_wrap
-
-
-def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer, total_num_steps):
-    if cfg.fsdp:
-        setup_fsdp_envs(cfg)
-    elif cfg.deepspeed:
-        os.environ["ACCELERATE_USE_DEEPSPEED"] = "true"
-
+def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer):
+    total_num_steps = int(
+        math.ceil(len(train_dataset) * cfg.num_epochs / cfg.batch_size)
+    )
    warmup_steps = (
        cfg.warmup_steps
        if cfg.warmup_steps is not None
@@ -537,11 +104,16 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer, total_num_
            training_arguments_kwargs["fsdp_config"] = dict(cfg.fsdp_config)

    # deepspeed
-    if cfg.deepspeed:
-        training_arguments_kwargs["deepspeed"] = cfg.deepspeed
-
-    if cfg.lr_quadratic_warmup is not None:
-        training_arguments_kwargs["lr_quadratic_warmup"] = cfg.lr_quadratic_warmup
+    if (
+        os.environ.get("ACCELERATE_USE_DEEPSPEED") == "true"
+        and torch.cuda.device_count() > 1
+    ):
+        if cfg.deepspeed:
+            training_arguments_kwargs["deepspeed"] = cfg.deepspeed
+        else:
+            # make a guess here
+            # TODO search Path("./") for one
+            training_arguments_kwargs["deepspeed"] = "./ds_config.json"

    if cfg.adam_beta1:
        training_arguments_kwargs["adam_beta1"] = cfg.adam_beta1
@@ -552,55 +124,11 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer, total_num_
    if cfg.max_grad_norm:
        training_arguments_kwargs["max_grad_norm"] = cfg.max_grad_norm

-    if cfg.hub_model_id:
-        training_arguments_kwargs["hub_model_id"] = cfg.hub_model_id
+    if cfg.push_to_hub_model_id:
+        training_arguments_kwargs["push_to_hub_model_id"] = cfg.push_to_hub_model_id
        training_arguments_kwargs["push_to_hub"] = True
-        training_arguments_kwargs["hub_private_repo"] = True

-        if cfg.hub_strategy:
-            training_arguments_kwargs["hub_strategy"] = cfg.hub_strategy
-
-    if cfg.save_safetensors:
-        training_arguments_kwargs["save_safetensors"] = cfg.save_safetensors
-
-    if cfg.sample_packing_eff_est:
-        training_arguments_kwargs[
-            "sample_packing_efficiency"
-        ] = cfg.sample_packing_eff_est
-
-    if cfg.val_set_size == 0:
-        training_arguments_kwargs["evaluation_strategy"] = "no"
-    elif cfg.eval_steps:
-        training_arguments_kwargs["evaluation_strategy"] = "steps"
-        training_arguments_kwargs["eval_steps"] = cfg.eval_steps
-    else:
-        # we have an eval set, but no steps defined, use epoch
-        training_arguments_kwargs["evaluation_strategy"] = "epoch"
-
-    if cfg.save_strategy:
-        training_arguments_kwargs["save_strategy"] = cfg.save_strategy
-    else:
-        training_arguments_kwargs["save_strategy"] = (
-            "steps" if cfg.save_steps else "epoch"
-        )
-
-    if cfg.do_bench_eval:
-        training_arguments_kwargs["do_bench_eval"] = cfg.do_bench_eval
-        if cfg.bench_dataset:
-            training_arguments_kwargs["bench_dataset"] = cfg.bench_dataset
-
-    # DDP Config
-    if cfg.ddp_timeout:
-        training_arguments_kwargs["ddp_timeout"] = cfg.ddp_timeout
-    # see https://pytorch.org/docs/stable/generated/torch.nn.parallel.DistributedDataParallel.html
-    if cfg.ddp_bucket_cap_mb:
-        training_arguments_kwargs["ddp_bucket_cap_mb"] = cfg.ddp_bucket_cap_mb
-    if cfg.ddp_broadcast_buffers is not None:
-        training_arguments_kwargs["ddp_broadcast_buffers"] = cfg.ddp_broadcast_buffers
-
-    training_args = AxolotlTrainingArguments(  # pylint: disable=unexpected-keyword-arg
-        max_steps=total_num_steps if cfg.max_steps else -1,
-        max_seq_length=cfg.sequence_len,
+    training_args = transformers.TrainingArguments(
        per_device_train_batch_size=cfg.micro_batch_size,
        per_device_eval_batch_size=cfg.eval_batch_size
        if cfg.eval_batch_size is not None
@@ -609,9 +137,12 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer, total_num_
        eval_accumulation_steps=cfg.gradient_accumulation_steps,
        num_train_epochs=cfg.num_epochs,
        learning_rate=cfg.learning_rate,
+        evaluation_strategy="steps",
+        save_strategy="steps" if cfg.save_steps else "epoch",
+        eval_steps=cfg.eval_steps,
        save_steps=cfg.save_steps,
        output_dir=cfg.output_dir,
-        save_total_limit=cfg.save_total_limit if cfg.save_total_limit else 4,
+        save_total_limit=3,
        load_best_model_at_end=(
            cfg.load_best_model_at_end is not False
            and cfg.val_set_size > 0
@@ -629,10 +160,6 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer, total_num_
        if cfg.lr_scheduler and cfg.lr_scheduler not in ("one_cycle", "log_sweep")
        else "cosine",
        weight_decay=cfg.weight_decay if cfg.weight_decay is not None else 0.0,
-        sample_packing=cfg.sample_packing if cfg.sample_packing else False,
-        sample_packing_seq_len_multiplier=cfg.micro_batch_size,
-        relora_steps=cfg.relora_steps,
-        relora_warmup_steps=cfg.relora_warmup_steps,
        **training_arguments_kwargs,
    )

@@ -642,13 +169,68 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer, total_num_
        if Path(cfg.torchdistx_path).exists():
            sys.path.append(cfg.torchdistx_path)
            importlib.import_module("torchdistx")
+    if (
+        cfg.optimizer == "adamw_bnb_8bit"
+        and not cfg.gptq
+        and "deepspeed" not in training_arguments_kwargs
+        and not cfg.fsdp
+    ):
+        decay_parameters = get_parameter_names(model, [nn.LayerNorm])
+        decay_parameters = [name for name in decay_parameters if "bias" not in name]
+        optimizer_grouped_parameters = [
+            {
+                "params": [
+                    p
+                    for n, p in model.named_parameters()
+                    if (n in decay_parameters and p.requires_grad)
+                ],
+                "weight_decay": training_args.weight_decay,
+            },
+            {
+                "params": [
+                    p
+                    for n, p in model.named_parameters()
+                    if (n not in decay_parameters and p.requires_grad)
+                ],
+                "weight_decay": 0.0,
+            },
+        ]
+
+        optimizer = bnb.optim.Adam8bit(
+            optimizer_grouped_parameters,
+            betas=(training_args.adam_beta1, training_args.adam_beta2),
+            eps=training_args.adam_epsilon,
+            lr=training_args.learning_rate,
+        )
+
+        if cfg.lr_scheduler == "one_cycle":
+            lr_scheduler_kwargs = (
+                cfg.lr_scheduler_kwargs if cfg.lr_scheduler_kwargs else {}
+            )
+            lr_scheduler = OneCycleLR(
+                optimizer,
+                cfg.learning_rate,
+                total_steps=total_num_steps,
+                epochs=cfg.num_epochs,
+                div_factor=cfg.lr_div_factor if cfg.lr_div_factor else 6,
+                **lr_scheduler_kwargs,
+            )
+        elif cfg.lr_scheduler == "log_sweep":
+            lr_scheduler = InterpolatingLogScheduler(
+                optimizer,
+                cfg.warmup_steps,
+                cfg.log_sweep_min_lr if cfg.log_sweep_min_lr else 1e-10,
+                cfg.log_sweep_max_lr if cfg.log_sweep_max_lr else 10,
+            )
+        else:
+            lr_scheduler = transformers.get_cosine_schedule_with_warmup(
+                optimizer,
+                training_args.warmup_steps,
+                total_num_steps,
+            )
+        trainer_kwargs["optimizers"] = (optimizer, lr_scheduler)

    callbacks = []
-    callbacks.append(GPUStatsCallback(cfg))
-
-    if cfg.relora_steps:
-        callbacks.append(ReLoRACallback(cfg))
-
    # TODO on_save callback to sync checkpoints to GCP/AWS in background
    if cfg.early_stopping_patience:
        early_stop_cb = EarlyStoppingCallback(
@@ -666,18 +248,16 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer, total_num_
        callbacks.append(SaveBetterTransformerModelCallback)

    data_collator_kwargs = {
-        "padding": True,  # True/"longest" is the default
+        "padding": True,
    }
-    if cfg.pad_to_sequence_len:
-        data_collator_kwargs["pad_to_multiple_of"] = 64 * math.ceil(
-            cfg.sequence_len / 64
-        )
+    if cfg.collator_pad_to_longest:
+        data_collator_kwargs["padding"] = "longest"
    else:
-        # A100 is best at 64, while others at 8. Let's use the larger so we don't have to check
-        # https://docs.nvidia.com/deeplearning/performance/dl-performance-matrix-multiplication/index.html
-        data_collator_kwargs["pad_to_multiple_of"] = 64
+        data_collator_kwargs["pad_to_multiple_of"] = 8

    if cfg.is_llama_derived_model and cfg.landmark_attention:
+        from functools import partial
+
        from axolotl.monkeypatch.llama_landmark_attn import (
            add_mem_tokens,
            get_mem_id,
@@ -686,7 +266,7 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer, total_num_

        set_model_mem_id(model, tokenizer)

-        LOG.info("Adding landmark attention tokens to dataset")
+        logging.info("Adding landmark attention tokens to dataset")

        for dataset in [train_dataset, eval_dataset]:
            dataset = dataset.map(
@@ -695,22 +275,17 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer, total_num_
                num_proc=32,
            )

-    trainer_cls = AxolotlTrainer
-    if cfg.lr_scheduler == "one_cycle" and (cfg.fsdp or cfg.adapter == "qlora"):
-        trainer_cls = OneCycleLRSchedulerTrainer
-    elif cfg.relora_steps:
-        trainer_cls = ReLoRATrainer
+    trainer_cls = (
+        OneCycleLRSchedulerTrainer
+        if cfg.lr_scheduler == "one_cycle" and (cfg.fsdp or cfg.adapter == "qlora")
+        else transformers.Trainer
+    )
    trainer = trainer_cls(
        model=model,
        train_dataset=train_dataset,
        eval_dataset=eval_dataset,
        args=training_args,
-        data_collator=DataCollatorForSeq2Seq(
-            tokenizer,
-            return_tensors="pt",
-            **data_collator_kwargs,
-        ),
-        bench_data_collator=transformers.DataCollatorForSeq2Seq(
+        data_collator=transformers.DataCollatorForSeq2Seq(
            tokenizer,
            return_tensors="pt",
            **data_collator_kwargs,
@@ -719,7 +294,4 @@ def setup_trainer(cfg, train_dataset, eval_dataset, model, tokenizer, total_num_
        **trainer_kwargs,
    )

-    if cfg.do_bench_eval:
-        trainer.add_callback(bench_eval_callback_factory(trainer, tokenizer))
-
    return trainer
--- a/src/axolotl/utils/validation.py
+++ b/src/axolotl/utils/validation.py
@@ -0,0 +1,105 @@
+"""Module for validating config files"""
+
+import logging
+
+import torch
+
+
+def validate_config(cfg):
+    if cfg.gradient_accumulation_steps and cfg.batch_size:
+        raise ValueError(
+            "please set only one of gradient_accumulation_steps or batch_size"
+        )
+    if cfg.batch_size:
+        logging.warning(
+            "%s\n%s",
+            "batch_size is not recommended. Please use gradient_accumulation_steps instead.",
+            "To calculate the equivalent gradient_accumulation_steps, divide batch_size / micro_batch_size / number of gpus.",
+        )
+    if cfg.load_4bit:
+        raise ValueError(
+            "cfg.load_4bit parameter has been deprecated and replaced by cfg.gptq"
+        )
+
+    if cfg.adapter == "qlora":
+        if cfg.merge_lora:
+            # can't merge qlora if loaded in 8bit or 4bit
+            if cfg.load_in_8bit:
+                raise ValueError("Can't merge qlora if loaded in 8bit")
+
+            if cfg.gptq:
+                raise ValueError("Can't merge qlora if gptq")
+
+            if cfg.load_in_4bit:
+                raise ValueError("Can't merge qlora if loaded in 4bit")
+
+        else:
+            if cfg.load_in_8bit:
+                raise ValueError("Can't load qlora in 8bit")
+
+            if cfg.gptq:
+                raise ValueError("Can't load qlora if gptq")
+
+            if not cfg.load_in_4bit:
+                raise ValueError("Require cfg.load_in_4bit to be True for qlora")
+
+    if not cfg.load_in_8bit and cfg.adapter == "lora":
+        logging.warning("We recommend setting `load_in_8bit: true` for LORA finetuning")
+
+    if cfg.trust_remote_code:
+        logging.warning(
+            "`trust_remote_code` is set to true. Please make sure that you reviewed the remote code/model."
+        )
+
+    if cfg.push_dataset_to_hub and cfg.hf_use_auth_token is not True:
+        raise ValueError(
+            "Require cfg.hf_use_auth_token to be True for push_dataset_to_hub"
+        )
+
+    if (cfg.base_model and "falcon" in cfg.base_model.lower()) and cfg.fsdp:
+        raise ValueError("FSDP is not supported for falcon models")
+
+    if (
+        cfg.base_model and "mpt" in cfg.base_model.lower()
+    ) and cfg.gradient_checkpointing:
+        raise ValueError("gradient_checkpointing is not supported for MPT models")
+
+    if cfg.flash_optimum is True:
+        if cfg.adapter:
+            logging.warning(
+                "BetterTransformers probably doesn't work with PEFT adapters"
+            )
+        if cfg.fp16 or cfg.bf16:
+            raise ValueError("AMP is not supported with BetterTransformer")
+        if cfg.float16 is not True and cfg.bloat16 is not True:
+            logging.warning(
+                "You should probably set bfloat16 or float16 to true to "
+                "load the model in float16 for BetterTransformers"
+            )
+        if int(torch.__version__.split(".")[0]) < 2:
+            logging.warning("torch>=2.0.0 required")
+            raise ValueError(
+                f"flash_optimum for BetterTransformers may not be used with {torch.__version__}"
+            )
+
+    if cfg.pretraining_dataset and cfg.group_by_length:
+        logging.warning(
+            "You probably want to disable group_by_length as it will force a streamed dataset to download completely."
+        )
+
+    if any([cfg.adamw_beta1, cfg.adamw_beta2, cfg.adamw_epsilon]) and (
+        not cfg.optimizer or "adamw" not in cfg.optimizer
+    ):
+        logging.warning("adamw hyperparameters found, but no adamw optimizer set")
+
+    # TODO
+    # MPT 7b
+    # https://github.com/facebookresearch/bitsandbytes/issues/25
+    # no 8bit adaAmw w bf16
+
+    # GPT-NeoX
+    # evals broken when extending context len
+    # File "/root/miniconda3/envs/py3.9/lib/python3.9/site-packages/transformers/models/gpt_neox/modeling_gpt_neox.py", line 162, in forward                        attn_output, attn_weights = self._attn(query, key, value, attention_mask, head_mask)
+    # File "/root/miniconda3/envs/py3.9/lib/python3.9/site-packages/optimum/bettertransformer/models/attention.py", line 74, in gpt2_wrapped_scaled_dot_product
+    # attention_mask = causal_mask + attention_mask
+    # RuntimeError: The size of tensor a (2048) must match the size of tensor b (8132) at non-singleton dimension 3
--- a/src/axolotl/utils/wandb.py
+++ b/src/axolotl/utils/wandb.py
@@ -9,8 +9,6 @@ def setup_wandb_env_vars(cfg):
    elif cfg.wandb_project and len(cfg.wandb_project) > 0:
        os.environ["WANDB_PROJECT"] = cfg.wandb_project
        cfg.use_wandb = True
-        if cfg.wandb_entity and len(cfg.wandb_entity) > 0:
-            os.environ["WANDB_ENTITY"] = cfg.wandb_entity
        if cfg.wandb_watch and len(cfg.wandb_watch) > 0:
            os.environ["WANDB_WATCH"] = cfg.wandb_watch
        if cfg.wandb_log_model and len(cfg.wandb_log_model) > 0:
--- a/tests/fixtures/conversation.tokenized_llama2chat.json
+++ b/tests/fixtures/conversation.tokenized_llama2chat.json
--- a/tests/monkeypatch/test_llama_attn_hijack_flash.py
+++ b/tests/monkeypatch/test_llama_attn_hijack_flash.py
@@ -1,30 +0,0 @@
-"""
-Unit tests for the monkeypatch utils
-"""
-import unittest
-
-import torch
-
-from axolotl.monkeypatch.utils import get_cu_seqlens, get_cu_seqlens_from_pos_ids
-
-
-class TestMonkeyPatchUtils(unittest.TestCase):
-    """
-    Unit test class for monkeypatch utils
-    """
-
-    def test_get_cu_seqlens_1d(self):
-        attn_mask = torch.tensor([[1, 1, 1, 1, 2, 2, 2, 3, 3, 3, 3, 3, 4, 4, 0, 0]])
-        target_res = torch.tensor([0, 4, 7, 12, 14, 16], dtype=torch.int32)
-        self.assertTrue(torch.allclose(get_cu_seqlens(attn_mask)[0], target_res))
-
-    def test_get_cu_seqlens_from_pos_ids_1d(self):
-        position_ids = torch.tensor([[0, 1, 2, 3, 0, 1, 2, 0, 1, 2, 3, 4, 0, 1, 0, 0]])
-        target_res = torch.tensor([0, 4, 7, 12, 14, 16], dtype=torch.int32)
-        self.assertTrue(
-            torch.allclose(get_cu_seqlens_from_pos_ids(position_ids)[0], target_res)
-        )
-
-
-if __name__ == "__main__":
-    unittest.main()
--- a/tests/test_dict.py
+++ b/tests/test_dict.py
@@ -72,13 +72,6 @@ class DictDefaultTest(unittest.TestCase):

        assert cfg.random_key is None, "DictDefault should return None for missing keys"

-    def test_dict_or(self):
-        cfg = DictDefault({}) | DictDefault({})
-
-        assert (
-            cfg.random_key is None
-        ), "DictDefault should return None for missing keys after | operation"
-
    def test_dict_nested_missingparentkey(self):
        """
        Due to subclassing Dict, DictDefault will error if we try to access a nested key whose parent key does not exist.
--- a/tests/test_expand_mask.py
+++ b/tests/test_expand_mask.py
@@ -1,44 +0,0 @@
-"""
-Unit tests for the monkey patch for expand mask to handle packed sequences
-"""
-import unittest
-
-import torch
-
-from axolotl.monkeypatch.llama_expand_mask import _expand_mask
-
-
-class TestExpandMask(unittest.TestCase):
-    """
-    Test class for attention mask expansion for packed sequences
-    """
-
-    def test_output(self):
-        mask = torch.tensor([[1, 1, 1, 2], [2, 3, 3, 0]])
-        dtype = torch.float32
-        expected_output = torch.tensor(
-            [
-                [
-                    [
-                        [0.0000e00, -3.4028e38, -3.4028e38, -3.4028e38],
-                        [0.0000e00, 0.0000e00, -3.4028e38, -3.4028e38],
-                        [0.0000e00, 0.0000e00, 0.0000e00, -3.4028e38],
-                        [-3.4028e38, -3.4028e38, -3.4028e38, 0.0000e00],
-                    ]
-                ],
-                [
-                    [
-                        [0.0000e00, -3.4028e38, -3.4028e38, -3.4028e38],
-                        [-3.4028e38, 0.0000e00, -3.4028e38, -3.4028e38],
-                        [-3.4028e38, 0.0000e00, 0.0000e00, -3.4028e38],
-                        [-3.4028e38, -3.4028e38, -3.4028e38, -3.4028e38],
-                    ]
-                ],
-            ]
-        )
-        # Check that the output matches the expected output
-        self.assertTrue(torch.allclose(_expand_mask(mask, dtype), expected_output))
-
-
-if __name__ == "__main__":
-    unittest.main()
--- a/tests/test_packed_dataset.py
+++ b/tests/test_packed_dataset.py
@@ -55,14 +55,10 @@ class TestPacking(unittest.TestCase):
        # first example doesn't have mask reset
        assert example["input_ids"][0] == self.tokenizer.bos_token_id
        assert example["attention_mask"][0] == 1
-        assert example["position_ids"][0] == 0
-        assert example["position_ids"][1] == 1

        # but subsequent one does
        assert example["input_ids"][next_bos_index] == self.tokenizer.bos_token_id
        assert example["attention_mask"][next_bos_index] == 2
-        assert example["position_ids"][next_bos_index] == 0
-        assert example["position_ids"][next_bos_index + 1] == 1


 if __name__ == "__main__":
--- a/tests/test_prompt_tokenizers.py
+++ b/tests/test_prompt_tokenizers.py
@@ -4,24 +4,20 @@ import logging
 import unittest
 from pathlib import Path

-from transformers import AutoTokenizer, LlamaTokenizer
+from transformers import AutoTokenizer

 from axolotl.prompt_strategies.alpaca_chat import NoSystemPrompter
 from axolotl.prompt_strategies.alpaca_w_system import (
    InstructionWSystemPromptTokenizingStrategy,
    SystemDataPrompter,
 )
-from axolotl.prompt_strategies.llama2_chat import (
-    Llama2ChatPrompter,
-    LLama2ChatTokenizingStrategy,
-)
 from axolotl.prompt_tokenizers import (
    AlpacaPromptTokenizingStrategy,
    ShareGPTPromptTokenizingStrategy,
 )
 from axolotl.prompters import AlpacaPrompter, PromptStyle, ShareGPTPrompter

-LOG = logging.getLogger("axolotl")
+logging.basicConfig(level="INFO")


 class TestPromptTokenizationStrategies(unittest.TestCase):
@@ -134,95 +130,8 @@ class InstructionWSystemPromptTokenizingStrategyTest(unittest.TestCase):
            "output": "Hi! How can I help?",
        }
        example = strat.tokenize_prompt(sample)
-        assert example["input_ids"][0:5] == [
-            1,
-            28962,
-            1254,
-            12665,
-            29901,
-        ]  # "<s>SYSTEM:"
-        assert example["input_ids"][5:7] == [671, 20118]  # " use cot"
-        assert example["input_ids"][8] == 11889  # USER
-
-
-class Llama2ChatTokenizationTest(unittest.TestCase):
-    """
-    Test class for prompt tokenization strategies with sys prompt from the dataset
-    """
-
-    def setUp(self) -> None:
-        # pylint: disable=duplicate-code
-        self.tokenizer = LlamaTokenizer.from_pretrained("NousResearch/Llama-2-7b-hf")
-        # woraround because official Meta repos are not open
-
-    def test_llama2_chat_integration(self):
-        with open(
-            Path(__file__).parent / "fixtures/conversation.json", encoding="utf-8"
-        ) as fin:
-            data = fin.read()
-            conversation = json.loads(data)
-        with open(
-            Path(__file__).parent / "fixtures/conversation.tokenized_llama2chat.json",
-            encoding="utf-8",
-        ) as fin:
-            data = fin.read()
-            tokenized_conversation = json.loads(data)
-        prompter = Llama2ChatPrompter()
-        strat = LLama2ChatTokenizingStrategy(
-            prompter,
-            self.tokenizer,
-            False,
-            4096,
-        )
-        example = strat.tokenize_prompt(conversation)
-        for fields in ["input_ids", "attention_mask", "labels"]:
-            self.assertEqual(len(example[fields]), len(tokenized_conversation[fields]))
-            self.assertEqual(example[fields], tokenized_conversation[fields])
-
-    def compare_with_transformers_integration(self):
-        # this needs transformers >= v4.31.0
-        from transformers.models.llama.tokenization_llama import B_SYS, E_SYS
-        from transformers.pipelines.conversational import Conversation
-
-        # from transformers.models.llama.tokenization_llama import DEFAULT_SYSTEM_PROMPT
-        # broken as of 23/7/20
-        # see https://github.com/huggingface/transformers/pull/24935
-        # pylint: disable=C0103
-        DEFAULT_SYSTEM_PROMPT = """\
-You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
-
-If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information."""
-        with open(
-            Path(__file__).parent / "fixtures/conversation.json", encoding="utf-8"
-        ) as fin:
-            data = fin.read()
-            conversation = json.loads(data)
-        with open(
-            Path(__file__).parent / "fixtures/conversation.tokenized_llama2chat.json",
-            encoding="utf-8",
-        ) as fin:
-            data = fin.read()
-            tokenized_conversation = json.loads(data)
-
-        user_input = []
-        answers = []
-        for msg in conversation["conversations"]:
-            if msg["from"] == "human":
-                user_input.append(msg["value"])
-            else:
-                answers.append(msg["value"])
-        hf_conf = Conversation(
-            text=user_input[-1],
-            past_user_inputs=[B_SYS + DEFAULT_SYSTEM_PROMPT + E_SYS + user_input[0]]
-            + user_input[1:-1],
-            generated_responses=answers,
-        )
-        # pylint: disable=W0212
-        hf_tokens = self.tokenizer._build_conversation_input_ids(hf_conf)
-
-        self.assertEqual(
-            hf_tokens, tokenized_conversation["input_ids"][: len(hf_tokens)]
-        )
+        assert example["input_ids"][0:3] == [1, 671, 20118]  # <s>use cot
+        assert example["input_ids"][3] == 11889  # USER


 if __name__ == "__main__":
--- a/tests/test_prompters.py
+++ b/tests/test_prompters.py
@@ -70,7 +70,7 @@ class AlpacaPrompterTest(unittest.TestCase):
            )
        )
        assert "use cot" in res
-        assert res.startswith("SYSTEM:")
+        assert res.startswith("use cot")
        assert "### Instruction:" not in res
        assert "### Input:" not in res
        assert "alpacas" in res
--- a/tests/test_tokenizers.py
+++ b/tests/test_tokenizers.py
@@ -13,22 +13,17 @@ class TestTokenizers(unittest.TestCase):
    """

    def test_default_use_fast(self):
-        cfg = DictDefault(
-            {
-                "tokenizer_config": "huggyllama/llama-7b",
-            }
-        )
-        tokenizer = load_tokenizer(cfg)
+        cfg = DictDefault({})
+        tokenizer = load_tokenizer("huggyllama/llama-7b", None, cfg)
        assert "Fast" in tokenizer.__class__.__name__

    def test_dont_use_fast(self):
        cfg = DictDefault(
            {
-                "tokenizer_config": "huggyllama/llama-7b",
                "tokenizer_use_fast": False,
            }
        )
-        tokenizer = load_tokenizer(cfg)
+        tokenizer = load_tokenizer("huggyllama/llama-7b", None, cfg)
        assert "Fast" not in tokenizer.__class__.__name__


--- a/tests/test_validation.py
+++ b/tests/test_validation.py
@@ -6,8 +6,8 @@ from typing import Optional

 import pytest

-from axolotl.utils.config import validate_config
 from axolotl.utils.dict import DictDefault
+from axolotl.utils.validation import validate_config


 class ValidationTest(unittest.TestCase):
@@ -268,7 +268,7 @@ class ValidationTest(unittest.TestCase):
        cfg = DictDefault(
            {
                "optimizer": None,
-                "adam_epsilon": 0.0001,
+                "adamw_epsilon": 0.0001,
            }
        )

@@ -283,7 +283,7 @@ class ValidationTest(unittest.TestCase):
        cfg = DictDefault(
            {
                "optimizer": "adafactor",
-                "adam_beta1": 0.0001,
+                "adamw_beta1": 0.0001,
            }
        )

@@ -298,9 +298,9 @@ class ValidationTest(unittest.TestCase):
        cfg = DictDefault(
            {
                "optimizer": "adamw_bnb_8bit",
-                "adam_beta1": 0.9,
-                "adam_beta2": 0.99,
-                "adam_epsilon": 0.0001,
+                "adamw_beta1": 0.0001,
+                "adamw_beta2": 0.0001,
+                "adamw_epsilon": 0.0001,
            }
        )

@@ -313,27 +313,3 @@ class ValidationTest(unittest.TestCase):
        )

        validate_config(cfg)
-
-    def test_packing(self):
-        cfg = DictDefault(
-            {
-                "max_packed_sequence_len": 2048,
-            }
-        )
-        with self._caplog.at_level(logging.WARNING):
-            validate_config(cfg)
-            assert any(
-                "max_packed_sequence_len will be deprecated in favor of sample_packing"
-                in record.message
-                for record in self._caplog.records
-            )
-
-        cfg = DictDefault(
-            {
-                "max_packed_sequence_len": 2048,
-                "sample_packing": True,
-            }
-        )
-        regex_exp = r".*set only one of max_packed_sequence_len \(deprecated soon\) or sample_packing.*"
-        with pytest.raises(ValueError, match=regex_exp):
-            validate_config(cfg)
Author	SHA1	Message	Date
Wing Lian	8028652b8f	fix attetion mask with packing Some checks failed pre-commit / pre-commit (push) Has been cancelled Details PyTest / test (3.10) (push) Has been cancelled Details PyTest / test (3.9) (push) Has been cancelled Details	2023-07-15 10:38:01 -04:00
Wing Lian	33814cc94e	make sure we eval for openorca	2023-07-02 17:59:10 -04:00
Wing Lian	50254a7ccc	handle orca splits	2023-07-01 07:20:23 -04:00