Model description
This model is a fine-tuned version of Qwen/Qwen2.5-32B-Instruct on the Bespoke-Stratos-17k dataset. 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. 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