|
|
---
|
|
|
base_model: Qwen/Qwen2.5-1.5B-Instruct
|
|
|
library_name: transformers
|
|
|
tags:
|
|
|
- generated_from_trainer
|
|
|
- trl
|
|
|
- grpo
|
|
|
licence: license
|
|
|
datasets:
|
|
|
- microsoft/orca-math-word-problems-200k
|
|
|
co2_eq_emissions:
|
|
|
emissions: 7100
|
|
|
source: https://mlco2.github.io/impact#compute
|
|
|
training_type: GRPO
|
|
|
geographical_location: East US2
|
|
|
hardware_used: 1 x H100 96GB
|
|
|
language:
|
|
|
- zho
|
|
|
- eng
|
|
|
- fra
|
|
|
- spa
|
|
|
- por
|
|
|
- deu
|
|
|
- ita
|
|
|
- rus
|
|
|
- jpn
|
|
|
- kor
|
|
|
- vie
|
|
|
- tha
|
|
|
- ara
|
|
|
model-index:
|
|
|
- name: Qwen2.5-1.5B-Thinking
|
|
|
results:
|
|
|
- task:
|
|
|
type: text-generation
|
|
|
dataset:
|
|
|
name: openai/gsm8k
|
|
|
type: GradeSchoolMath8K
|
|
|
metrics:
|
|
|
- type: GSM8k (0-Shot)
|
|
|
value: 14.4%
|
|
|
name: GSM8k (0-Shot)
|
|
|
- type: GSM8k (Few-Shot)
|
|
|
value: 63.31%
|
|
|
name: GSM8k (Few-Shot)
|
|
|
---
|
|
|
|
|
|
# Model Card for Qwen2.5-1.5B-Thinking
|
|
|
|
|
|
Improved Model at [Qwen2.5-1.5B-Thinking-v1.1](https://huggingface.co/justinj92/Qwen2.5-1.5B-Thinking-v1.1).
|
|
|
It has been trained using [TRL](https://github.com/huggingface/trl).
|
|
|
|
|
|
|
|
|
## Evals
|
|
|
|
|
|
| Model | GSM8k 0-Shot | GSM8k Few-Shot |
|
|
|
|------------------------------------------|------------------|-------------------|
|
|
|
| Mistral-7B-v0.1 | 10 | 41 |
|
|
|
| Qwen2.5-1.5B-Thinking | 14.4 | 63.31 |
|
|
|
|
|
|
|
|
|
## Training procedure
|
|
|
|
|
|
<img src="https://raw.githubusercontent.com/wandb/wandb/fc186783c86c33980e5c73f13363c13b2c5508b1/assets/logo-dark.svg" alt="Weights & Biases Logged" width="150" height="24"/>
|
|
|
|
|
|
<img src="https://huggingface.co/justinj92/Qwen2.5-1.5B-Thinking/resolve/main/w%26b_qwen_r1.png" width="1200" height="900"/>
|
|
|
|
|
|
Trained on 1xH100 96GB via Azure Cloud (East US2).
|
|
|
|
|
|
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
|
|
|
|
|
|
### Usage Recommendations
|
|
|
|
|
|
**Recommend adhering to the following configurations when utilizing the models, including benchmarking, to achieve the expected performance:**
|
|
|
|
|
|
1. Set the temperature within the range of 0.5-0.7 (0.6 is recommended) to prevent endless repetitions or incoherent outputs.
|
|
|
2. **For mathematical problems, it is advisable to include a directive in your prompt such as: "Please reason step by step, and put your final answer within \boxed{}."**
|
|
|
3. When evaluating model performance, it is recommended to conduct multiple tests and average the results.
|
|
|
4. This model is not enhanced for other domains apart from Maths.
|
|
|
|
|
|
### Framework versions
|
|
|
|
|
|
- TRL: 0.15.0.dev0
|
|
|
- Transformers: 4.49.0.dev0
|
|
|
- Pytorch: 2.5.1
|
|
|
- Datasets: 3.2.0
|
|
|
- Tokenizers: 0.21.0
|
|
|
|
|
|
## Citations
|
|
|
|
|
|
Cite GRPO as:
|
|
|
|
|
|
```bibtex
|
|
|
@article{zhihong2024deepseekmath,
|
|
|
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
|
|
|
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
|
|
|
year = 2024,
|
|
|
eprint = {arXiv:2402.03300},
|
|
|
}
|
|
|
|
|
|
```
|
|
|
|
|
|
Cite TRL as:
|
|
|
|
|
|
```bibtex
|
|
|
@misc{vonwerra2022trl,
|
|
|
title = {{TRL: Transformer Reinforcement Learning}},
|
|
|
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
|
|
|
year = 2020,
|
|
|
journal = {GitHub repository},
|
|
|
publisher = {GitHub},
|
|
|
howpublished = {\url{https://github.com/huggingface/trl}}
|
|
|
}
|
|
|
``` |
