Kashmary/mistral-mathqa-lora

Model description

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the \n [10th Math-I, 10th Math-II, 12th Math-I,12th Math-II] datasets in https://github.com/sheikhshafayat/BEnQA

Notebooks

Trained using LLaMA-Factory \n Training Notebook: https://colab.research.google.com/drive/1Muu_TP5qp09mAH6cBRnwpbxGPjKzYU8T?usp=sharing \n Testing Notebook: https://www.kaggle.com/code/anowersha/testing-kashmary-mistral-mathqa-lora

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0002
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• num_epochs: 3.0

Framework versions

• PEFT 0.15.2
• Transformers 4.52.4
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1