# ScienceLLaMA-3B

• 🤗 Data • 🤗 ScienceLLaMA-3B • 🤗 ScienceLLaMA-1B • 🐱 Code • 📃 Paper

This model is a fine-tuned with **Logits-Based Finetuning** on the [JingyaoLi/Science-Logits-1.2M](https://huggingface.co/datasets/JingyaoLi/Science-Logits-1.2M), which integrates the strengths of supervised learning and knowledge distillation by combining teacher logits with ground truth labels. This preserves both correctness and linguistic diversity.

## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-06 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 8 - gradient_accumulation_steps: 4 - total_train_batch_size: 256 - total_eval_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 1 ### Training results

### Framework versions - Transformers 4.45.0 - Pytorch 2.4.0+cu121 - Datasets 2.21.0 - Tokenizers 0.20.1

Full Model Card (README)