Skip to content

Issues: allenai/open-instruct

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

18 Open 129 Closed
18 Open 129 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Potential bug in gradient accumulation
#495 opened Dec 26, 2024 by yxchng
Is there any easy way to add full eval data evaluation every n iterations to RLVR?
#494 opened Dec 25, 2024 by yxchng
tulu3 preference data pipeline which in report is inconsistent with this code-repo
#491 opened Dec 19, 2024 by scattw
Recommendations for multi-node training of a 7B model with RL
#487 opened Dec 17, 2024 by zhudefa
1
SFT Loss unable to decrease on MATH data
#482 opened Dec 10, 2024 by yxchng
1
Request for Access to answer_extraction_model
#480 opened Dec 9, 2024 by iseesaw
1
Questions about hyperparameters in Llama-3.1-Tulu-3-8B Reproduction
#477 opened Dec 6, 2024 by wgimperial
4
Suggestions for Training a SFT Model with Extremely Long Contexts (8k–64k Tokens)
#476 opened Dec 6, 2024 by zhudefa
Will you support fine-tuning from olmo2?
#467 opened Dec 1, 2024 by zhudefa
1
TULU3 MATH eval
#465 opened Nov 30, 2024 by ypwang61
1
What exactly have you done with MergeKit?
#463 opened Nov 29, 2024 by sunshicheng1
2
DPO/PPO/etc should default to HF chat template
#458 opened Nov 25, 2024 by hamishivi
1
Error when evaluating the qlora-merged model.
#427 opened Nov 12, 2024 by vhientran
Some errors when doing evaluation with hf models
#352 opened Sep 16, 2024 by JiaQiSJTU
1
Problems about resuming from checkpoint for finetune_with_lora
#330 opened Sep 4, 2024 by ypwang61
1
Add a train field to training data enhancement New feature or request
#283 opened Aug 23, 2024 by hamishivi
2
Make faster docker build
#280 opened Aug 21, 2024 by vwxyzjn
Make open-instruct pip installable enhancement New feature or request
#276 opened Aug 19, 2024 by yakazimir
1
ProTip! Exclude everything labeled bug with -label:bug.