Skip to content

Issues: huggingface/trl

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

60 Open 844 Closed
60 Open 844 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
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

how to save v_head
#1650 opened May 20, 2024 by zyzhang1130
Adapter name for SFT trainer
#1649 opened May 18, 2024 by para-zhou
Set seed
#1648 opened May 17, 2024 by user799595
ValueError when training on a multi GPU setup and DPO
#1645 opened May 16, 2024 by miosturu
How to save and resume a checkpoint from PPOTrainer
#1643 opened May 14, 2024 by paraGONG
ImportError: cannot import name 'DPOConfig' from 'trl'
#1642 opened May 14, 2024 by AswiniNLP
10
Do we need to consider the chat template when doing DPO/KTO training?
#1640 opened May 11, 2024 by ZeroYuHuang
ImportError: cannot import name 'SFTConfig' from 'trl'
#1639 opened May 11, 2024 by brand17
2
When I used galore on orpo, the learning rate was set to 8e-6, but the training rate was 0.01
#1638 opened May 10, 2024 by Minami-su
How to use trl\trainer\kto_trainer.py
#1635 opened May 9, 2024 by mazhengyufreedom
3
Seq2SeqTrainer with DataCollatorForCompletionOnlyLM: incorrect masking for evaluation
#1634 opened May 8, 2024 by adamamer20
Seq2seq model with ppo_trainer samples strange output!
#1633 opened May 8, 2024 by sajastu
DDPO cannot use SDXL
#1630 opened May 8, 2024 by mao-code
PPOTrainer ignores data_collator keyword argument and uses provided collator inconsistently
#1629 opened May 8, 2024 by codezakh
Custom DPO Trainer CUDA OOM
#1626 opened May 7, 2024 by TheGhoul21
1
Learning to generate EOS tokens
#1623 opened May 6, 2024 by vwxyzjn
4
ConstantLengthDataset Ignore Some Texts
#1621 opened May 4, 2024 by TianyiPeng
kto error when assign dataset to device
#1620 opened May 4, 2024 by mostafamdy
2
Long data length cause Cuda ouf of memory when DPO training
#1619 opened May 4, 2024 by virt9
Have trouble in ppo example
#1618 opened May 3, 2024 by Shiguang-Guo
4
Error when Using 8-bit Quantization
#1616 opened May 3, 2024 by JhonDan1999
[enhancement] Implement IRPO training custom loss
#1611 opened May 1, 2024 by TheGhoul21
1
Training stops early
#1601 opened Apr 30, 2024 by Techinix
CLI utils class cases seem to be incorrect
#1600 opened Apr 29, 2024 by busycalibrating
2
[Question]How should I combine DPOTrainer and Accelerate for training?
#1597 opened Apr 29, 2024 by YangsongLan
ProTip! Exclude everything labeled bug with -label:bug.