N11100/deepseek-r1-python-code-ft

1---2library_name: peft3license: mit4base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B5tags:6- base_model:adapter:deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B7- lora8- transformers9pipeline_tag: text-generation10model-index:11- name: deepseek-r1-python-code-ft12  results: []13thumbnail: https://huggingface.co/N11100/deepseek-r1-python-code-ft/resolve/main/thumbnail.png14github: https://github.com/hubgunter4-ops/deepseek-r1-python-code-ft15inference: true16widget:17- text: "Explain how to secure a linux server."18  example_title: "Security Best Practices"19---20 21<!-- This model card has been generated automatically according to the information the Trainer had access to. You22should probably proofread and complete it, then remove this comment. -->23 24# deepseek-r1-python-code-ft25 26This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) on an unknown dataset.27 28## Model description29 30More information needed31 32## Intended uses & limitations33 34More information needed35 36## Training and evaluation data37 38More information needed39 40## Training procedure41 42### Training hyperparameters43 44The following hyperparameters were used during training:45- learning_rate: 0.000246- train_batch_size: 447- eval_batch_size: 848- seed: 4249- gradient_accumulation_steps: 450- total_train_batch_size: 1651- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments52- lr_scheduler_type: linear53- num_epochs: 154- mixed_precision_training: Native AMP55 56### Training results57 58 59 60### Framework versions61 62- PEFT 0.19.163- Transformers 5.9.064- Pytorch 2.11.0+cu12865- Datasets 4.0.066- Tokenizers 0.22.2