|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: Qwen/Qwen2.5-32B-Instruct |
|
tags: |
|
- llama-factory |
|
- full |
|
- generated_from_trainer |
|
model-index: |
|
- name: original |
|
results: [] |
|
language: |
|
- en |
|
datasets: |
|
- bespokelabs/Bespoke-Stratos-17k |
|
--- |
|
|
|
<p align="center"> |
|
<img src="https://huggingface.co./bespokelabs/Bespoke-MiniCheck-7B/resolve/main/Bespoke-Labs-Logo.png" width="550"> |
|
</p> |
|
|
|
## Model description |
|
This model is a fine-tuned version of [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co./Qwen/Qwen2.5-32B-Instruct) on the [Bespoke-Stratos-17k dataset](https://huggingface.co./datasets/bespokelabs/Bespoke-Stratos-17k). |
|
The dataset is derived by distilling DeepSeek-R1 using the data pipeline of Berkeley NovaSky’s Sky-T1 with some modifications. More info in the dataset card at [Bespoke-Stratos-17k](https://huggingface.co./datasets/bespokelabs/Bespoke-Stratos-17k). |
|
It outperforms Qwen-2.5-32B-Instruct on reasoning benchmarks: |
|
|
|
| Metric | Bespoke-Stratos-32B | Sky-T1-32B | o1-preview | DeepSeek-R1 | DeepSeek-R1-Distill-Qwen-32B (Ours // Reported)| |
|
|---|---|---|---|---|---| |
|
| AIME2024 | 63.3 | 43.3 | 40.0 | 79.8 | 66.7 // 72.6 | |
|
| MATH500 | 93.0 | 82.4 | 81.4 | 97.3 | 89.8 // 94.3 | |
|
| GPQA-Diamond | 58.1 | 56.8 | 75.2 | 71.5 | 61.1 // 62.1 | |
|
| LCB v2 Easy | 96.7 | 86.3 | 92.9 | - | 91.2 // - | |
|
| LCB v2 Medium | 75.2 | 56.8 | 54.9 | - | 75.7 // - | |
|
| LCB v2 Hard | 26.2 | 17.9 | 16.3 | - | 38.2 // - | |
|
| LCB v2 All | 71.1 | 57.9 | 59.1 | - | 72.2 // - | |
|
|
|
## Intended uses & limitations |
|
Apache 2.0 License |
|
|
|
|
|
## Training procedure |
|
We used 8xH100 to train the model for 27 hours. |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 1e-05 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 8 |
|
- gradient_accumulation_steps: 12 |
|
- total_train_batch_size: 96 |
|
- total_eval_batch_size: 64 |
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 3.0 |
|
|
|
### Training results |
|
|
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.1 |
|
- Pytorch 2.5.1+cu124 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.20.3 |
