--- model-index: - name: MetaMath-LoRA-LLaMA-7B results: - task: type: text-generation dataset: name: meta-math/MetaMathQA type: meta-math/MetaMathQA metrics: - name: Accuracy (zero-shot) type: Accuracy (zero-shot) value: 0.635 verified: true source: name: Arithmetic Reasoning on GSM8K url: https://paperswithcode.com/sota/arithmetic-reasoning-on-gsm8k license: apache-2.0 --- # Fine-tune LLaMA 2 (7B) with LoRA on meta-math/MetaMathQA Fine-tune for two epochs ## Result: **Reload the saved adapter**: Invalid output length: 3, Testing length: 1319, **Accuracy: 0.635** ## Comparison The official report **accuracy is 0.665** by fine-tuning the whole LLaMA 2 7B model for 3 epochs. **Note**: The LoRA adapter is being used for future research purposes. # 🚀 Adapter Usage ```python # Load the Pre-trained LoRA Adapter model.load_adapter("shuyuej/metamath_lora_llama2_7b_2_epoch") model.enable_adapters() ```