| library_name: peft | |
| license: mit | |
| base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B | |
| tags: | |
| - generated_from_trainer | |
| model-index: | |
| - name: multi-gpu-14b | |
| results: [] | |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You | |
| should probably proofread and complete it, then remove this comment. --> | |
| # multi-gpu-14b | |
| This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-14B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B) on an unknown dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 0.1943 | |
| ## Model description | |
| More information needed | |
| ## Intended uses & limitations | |
| More information needed | |
| ## Training and evaluation data | |
| More information needed | |
| ## Training procedure | |
| ### Training hyperparameters | |
| The following hyperparameters were used during training: | |
| - learning_rate: 0.0002 | |
| - train_batch_size: 1 | |
| - eval_batch_size: 1 | |
| - seed: 42 | |
| - gradient_accumulation_steps: 8 | |
| - total_train_batch_size: 8 | |
| - optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments | |
| - lr_scheduler_type: linear | |
| - num_epochs: 3 | |
| ### Training results | |
| | Training Loss | Epoch | Step | Validation Loss | | |
| |:-------------:|:------:|:----:|:---------------:| | |
| | 0.23 | 0.7529 | 200 | 0.2271 | | |
| | 0.1856 | 1.5045 | 400 | 0.2025 | | |
| | 0.1521 | 2.2560 | 600 | 0.1943 | | |
| ### Framework versions | |
| - PEFT 0.14.0 | |
| - Transformers 4.56.1 | |
| - Pytorch 2.5.1+cu121 | |
| - Datasets 4.0.0 | |
| - Tokenizers 0.22.0 |