|
--- |
|
library_name: transformers |
|
datasets: |
|
- BAAI/TACO |
|
- tasksource/PRM800K |
|
language: |
|
- en |
|
base_model: |
|
- Qwen/Qwen2.5-32B-Instruct |
|
- NovaSky-AI/Sky-T1-32B-Preview |
|
license: apache-2.0 |
|
--- |
|
|
|
## Model Details |
|
|
|
### Model Description |
|
|
|
<!-- Provide a longer summary of what this model is. --> |
|
|
|
This is a 32B reasoning model preference optimized on top of Sky-T1-32B-Preview to significantly reduce generation lengths while maintaining accuracy. The performance is on par with o1-preview model in both math and coding, while reducing generation lengths by up to 57% relative to Sky-T1-32B-Preview. |
|
Please see our [blog post](https://novasky-ai.github.io/posts/reduce-overthinking/) for more details. |
|
|
|
- **Developed by:** NovaSky Team from Sky Computing Lab at UC Berkeley. |
|
|
|
## Training Details |
|
|
|
### Training Data |
|
|
|
10K preference pairs in math and coding domains, generated by Sky-T1-32B-Preview. |
|
|
|
### Training Procedure |
|
We perform Simple Policy Optimization (SimPO) with a batch size of 96, learning rate of 5e-7, gamma of 0.3, and beta of 2.0. |
|
|
|
#### Speeds |
|
|
|
We use Llama-Factory for training. On 8xH100, the SimPO training takes ~2.5 hours with DeepSpeed Zero-3 Offload. |
|
|
|
|
|
## Evaluation |
|
| | | Sky-T1-32B-Preview | Sky-T1-32B-Flash | Qwen2.5-32B-Instruct | QwQ-32B- Base | DeepSeek-R1-Distill-Qwen-32B | |
|
|--------------|---------|:------------------:|:----------------:|:--------------------:|:-------------:|:----------------------------:| |
|
| Math500 | Acc | 88.6 | 88.6 | 76.2 | 89.2 | 90.8 | |
|
| | Avg Len | 2124 | 1417 (-33%) | 522 | 2089 | 2010 | |
|
| AIME24 | Acc | 43.3 | 43.3 | 16.7 | 50 | 66.7 | |
|
| | Avg Len | 6881 | 4365 (-37%) | 970 | 7379 | 9173 | |
|
| LCB Easy | Acc | 87.4 | 89 | 84.6 | 90.7 | 91.2 | |
|
| | Avg Len | 3415 | 2265 (-34%) | 414 | 3255 | 2775 | |
|
| LCB Medium | Acc | 56.8 | 56.3 | 40.8 | 56.3 | 76.7 | |
|
| | Avg Len | 8263 | 4389 (-47%) | 535 | 6742 | 6324 | |
|
| LCB Hard | Acc | 17.9 | 17.9 | 9.8 | 17.1 | 38.2 | |
|
| | Avg Len | 14564 | 6199 (-57%) | 618 | 10450 | 10448 | |
|
| MMLU | Acc | 82.4 | 81.7 | 80.1 | 85.2 | 82.1 | |
|
| | Avg Len | 1087 | 799 (-17%) | 312 | 1041 | 774 | |
|
| GPQA Diamond | Acc | 56.8 | 56.6 | 45.5 | 52.5 | 62.6 | |
|
| | Avg Len | 3503 | 2148 (-39%) | 600 | 3302 | 5108 | |
|
|
|
## Acknowledgement |
|
We would like to thanks the compute resources from [Lambda Lab](https://lambdalabs.com/service/gpu-cloud?srsltid=AfmBOop5FnmEFTkavVtdZDsLWvHWNg6peXtat-OXJ9MW5GMNsk756PE5) and [AnyScale](https://www.anyscale.com/). |
|
|
|
## License |
|
Apache-2.0 |
|
|
|
## Citation |
|
Please considering citing our blog post if you found it useful for your research. Thank you! |
|
|
|
```bibtex |
|
@misc{reduce_overthinking_2025, |
|
author = {NovaSky Team}, |
|
title = {Think Less, Achieve More: Cut Reasoning Costs by 50% Without Sacrificing Accuracy}, |
|
howpublished = {https://novasky-ai.github.io/posts/reduce-overthinking}, |
|
note = {Accessed: 2025-01-23}, |
|
year = {2025} |
|
} |
|
|
