Skip to content

Issues: agentica-project/deepscaler

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

34 Open 9 Closed
34 Open 9 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

Adapt to fewer GPUs
#47 opened Feb 25, 2025 by haoyangliu123
torch.float16 and torch.bfloat16 dtypes
#45 opened Feb 25, 2025 by zhl606
🎉 Reproduce the results successfully, avg score 56.4
#44 opened Feb 25, 2025 by JunnYu
6
Is there any plan for updating vllm to 0.7.x?
#43 opened Feb 24, 2025 by RyanLiu112
1
Train on a larger model?（14b、32b）
#42 opened Feb 24, 2025 by youyc22
1
Restart from ckpt: set training data
#39 opened Feb 19, 2025 by Doris2022
3
Batch size and throughput-related hyperparameters
#38 opened Feb 19, 2025 by cliangyu
3
dataset question
#37 opened Feb 18, 2025 by AnnaGolubeva
1
Model checkpoints
#36 opened Feb 17, 2025 by RicardoDominguez
2
Question about task difficulty in the dataset
#34 opened Feb 17, 2025 by chunhuizhang
1
Reproduce deepscaler
#33 opened Feb 17, 2025 by merlinarer
9
How to set dtype=half?
#32 opened Feb 16, 2025 by Hermi-Mire
1
oom when update_policy
#30 opened Feb 15, 2025 by zjhthu
15
Extremely Long Execution Time per Step
#29 opened Feb 15, 2025 by hodachi-axcxept
12
Packege Conflicts in Environment Installation
#28 opened Feb 15, 2025 by YangLH49
3
Is KL penalty really used in training?
#26 opened Feb 14, 2025 by samjia2000
1
Continue training for a coder model
#24 opened Feb 14, 2025 by abdelkrimkr
2
continue training and longer length
#23 opened Feb 13, 2025 by ypwang61
2
Can I reuse this project on other domain with new dataset ?
#22 opened Feb 13, 2025 by jskcnsl
1
Performance on Out-of-Distribution Datasets
#21 opened Feb 13, 2025 by biandh
1
Modification Details on VERL
#20 opened Feb 13, 2025 by zmy
3
Why isn't the <think> and <answer> tag used in the data's prompt?
#19 opened Feb 13, 2025 by OKC13
2
Questions regarding RL-trained 1.5B model's self-reflection and Qwen base model
#18 opened Feb 13, 2025 by zpqiu
3
Environment Installation Problems
#17 opened Feb 12, 2025 by hushyangqing
2
Evaluation Results Are Zero Due to Format Inconsistency in DeepSeek-R1-Distill-Qwen-1.5B
#16 opened Feb 12, 2025 by junkangwu
3
ProTip! What’s not been updated in a month: updated:<2025-01-25.