| --- |
| library_name: transformers |
| license: apache-2.0 |
| base_model: bespokelabs/Bespoke-Stratos-32B |
| 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 |
