Skip to content

Issues: princeton-nlp/LESS

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

13 Open 23 Closed
13 Open 23 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

Error when using fast_jl
#39 opened Nov 13, 2024 by xianglinyang
Can this model be used in the field of image classification?
#38 opened Nov 1, 2024 by fvdhsss
In Step 1: Warmup training，multiple gpu's trainning
#37 opened Oct 29, 2024 by xavierdawn
Are these processed data selected by Llama2-7b?
#36 opened Oct 26, 2024 by cafeii
Can you provide a validation dataset?
#35 opened Oct 25, 2024 by kuang1216
The issue with the Data Selection Pipeline
#33 opened Oct 18, 2024 by kuang1216
6
Differences in Model Performance When Reproducing Experiment
#32 opened Oct 16, 2024 by fannie1208
4
Why does the CSV extracted according to the steps show all the scores as nan?
#27 opened Sep 19, 2024 by SsmallSong
2
Discrepancy in Model Performance When Reproducing Experiment
#25 opened Aug 16, 2024 by tangzhy
1
At step1, single GPU works while multiple GPUs get stuck.
#22 opened Jun 28, 2024 by timturing
2
Questions about the influence value
#21 opened Jun 11, 2024 by simplelifetime
1
No optimizer.bin in Step 2
#18 opened May 20, 2024 by mihara-bot
3
step 2 when run "/get_train_lora_grads.sh", load the optimizer.pt error is happend
#4 opened Feb 23, 2024 by victorjiax
19
ProTip! no:milestone will show everything without a milestone.