Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Appearance settings

Update DPO debug scripts and add production script#1449

Merged
finbarrtimbers merged 5 commits intomainallenai/open-instruct:mainfrom
finbarr/dpo-mfu-pr7-debug-scriptsallenai/open-instruct:finbarr/dpo-mfu-pr7-debug-scriptsCopy head branch name to clipboard
Feb 12, 2026
Merged

Update DPO debug scripts and add production script#1449
finbarrtimbers merged 5 commits intomainallenai/open-instruct:mainfrom
finbarr/dpo-mfu-pr7-debug-scriptsallenai/open-instruct:finbarr/dpo-mfu-pr7-debug-scriptsCopy head branch name to clipboard

Conversation

@finbarrtimbers
Copy link
Copy Markdown
Collaborator

@finbarrtimbers finbarrtimbers commented Jan 30, 2026

Summary

  • Add --try_auto_save_to_beaker false to single_gpu.sh
  • Update multi_node.sh with budget checkpointing, compile_model, and disable eval/upload flags
  • Add new production DPO script for OLMo3-7B (scripts/train/olmo3/7b_instruct_dpo_olmocore.sh)

Note: The multi_node.sh script uses features from PRs 2-5 (gradient_checkpointing_mode, compile_model, etc.) and should be merged after those PRs.

Test plan

  • Run make style && make quality
  • Shellcheck passed

Runs

  • Single GPU DPO: Beaker
  • Multi-node DPO: Requires PRs 2-5 to be merged first (uses budget checkpointing, compile_model flags)

🤖 Generated with Claude Code

@chatgpt-codex-connector
Copy link
Copy Markdown

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.

@gemini-code-assist
Copy link
Copy Markdown
Contributor

Summary of Changes

Hello @finbarrtimbers, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request refines the DPO (Direct Preference Optimization) training environment by updating existing debug scripts and introducing a new production-ready script. The changes aim to improve resource management through budget-based gradient checkpointing and model compilation, while also providing finer control over Beaker-related functionalities like evaluation job launches and automatic saving. A significant addition is the dedicated script for training the OLMo3-7B model with DPO in a multi-node, production setting.

Highlights

  • single_gpu.sh Update: Disabled automatic saving to Beaker by adding --try_auto_save_to_beaker false.
  • multi_node.sh Enhancements: Introduced budget-based gradient checkpointing, enabled model compilation, and explicitly disabled Beaker evaluation job launches, pushing to hub, and automatic saving.
  • New Production DPO Script: Added scripts/train/olmo3/7b_instruct_dpo_olmocore.sh for training OLMo3-7B with DPO using OLMo-core, including detailed configuration for a multi-node setup.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help /gemini help Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.

Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request updates DPO debug scripts and adds a new production script. My review identifies a critical bug in the new production script that would cause it to fail due to a missing line continuation character. I've also pointed out several medium-severity issues related to shell scripting best practices, such as quoting variables and maintaining consistency in flag values across scripts. Code suggestions are provided to address these points.

Comment thread scripts/train/debug/dpo/multi_node.sh Outdated
Comment thread scripts/train/olmo3/7b_instruct_dpo_olmocore.sh Outdated
Comment thread scripts/train/olmo3/7b_instruct_dpo_olmocore.sh Outdated
Comment thread scripts/train/olmo3/7b_instruct_dpo_olmocore.sh Outdated
Comment thread scripts/train/olmo3/7b_instruct_dpo_olmocore.sh Outdated
Comment thread scripts/train/olmo3/7b_instruct_dpo_olmocore.sh Outdated
- Add --try_auto_save_to_beaker false to single_gpu.sh
- Update multi_node.sh with budget checkpointing, compile_model, and disable eval/upload flags
- Add new production DPO script for OLMo3-7B (7b_instruct_dpo_olmocore.sh)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
@finbarrtimbers finbarrtimbers force-pushed the finbarr/dpo-mfu-pr7-debug-scripts branch from c9ef28c to c50117b Compare January 31, 2026 00:01
finbarrtimbers and others added 4 commits February 12, 2026 07:10
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Remove --gradient_checkpointing and --gradient_checkpointing_mode
  (nonexistent in dpo.py; --activation_memory_budget handles this)
- Remove --compile_model (defaults to True already)
- Replace deprecated --tokenizer_name with --tokenizer_name_or_path

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
@finbarrtimbers finbarrtimbers requested review from hamishivi and natolambert and removed request for natolambert February 12, 2026 15:23
Copy link
Copy Markdown
Collaborator

@hamishivi hamishivi left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

l
g
t
m
!

--env NCCL_IB_RETRY_CNT=7 \
--num_nodes 4 \
--budget ai2/oe-adapt \
--gpus 8 -- torchrun \
Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

oh, interesting we launch with torchrun!

@finbarrtimbers finbarrtimbers added this pull request to the merge queue Feb 12, 2026
Merged via the queue into main with commit 6a0a483 Feb 12, 2026
7 checks passed
@finbarrtimbers finbarrtimbers deleted the finbarr/dpo-mfu-pr7-debug-scripts branch February 12, 2026 18:10
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants

Morty Proxy This is a proxified and sanitized view of the page, visit original site.