Downloads · 30 days
1
3% of all-time downloads
maas-grpo-qwen05b-fix1
sparsh122/maas-grpo-qwen05b-fix1
maas-grpo-qwen05b-fix1 is a machine learning model from sparsh122. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
- model: Qwen/Qwen2-0.5B-Instruct - epochs: 1 - batch size: 2 - gradient accumulation steps: 1 - num generations: 2 - learning rate: 5e-06 - temperature: 0.7 - topp: 0.9 - dataset size: 7 - prompt format: chatmessages…
All-time downloads
33
Public
Parameters
494M
1000 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors988 MB · 99%
At a glance
- Model type
- qwen2
- Access
- Public
- Created
- Apr 25, 2026
- Updated
- Apr 25, 2026
- SHA
- ecf51c99
Model card
From the Hugging Face model README
MAAS GRPO Run
- model:
Qwen/Qwen2-0.5B-Instruct - epochs:
1 - batch size:
2 - gradient accumulation steps:
1 - num generations:
2 - learning rate:
5e-06 - temperature:
0.7 - top_p:
0.9 - dataset size:
7 - prompt format:
chat_messages - log completions:
True - output dir:
/workspace/out - train metrics:
{"total_flos": 0.0, "train_loss": 0.027854227593966892, "train_runtime": 51.2644, "train_samples_per_second": 0.137, "train_steps_per_second": 0.137}
- Type
- qwen2
- Created
- Apr 25, 2026
- Updated
- Apr 25, 2026