--- library_name: transformers license: gemma base_model: google/gemma-2-2b-it tags: - trl - sft - generated_from_trainer model-index: - name: Gemma2b-v1.0-sft results: [] --- ## IMPORTANT !! I strongly recommend using the **DPO model** instead, as it is optimized for better performance and efficiency. This model has been fine-tuned for improved results, making it the preferred choice. Please refrain from using the **SFT model** unless you specifically need a base model to build upon. If you require a strong starting point for further fine-tuning, the SFT model can serve that purpose, but for general use, the DPO model is the better option. [Visualize in Weights & Biases](https://wandb.ai/wasamikiruasan-myself/Gemma/runs/vmsohspl?apiKey=69155ba82ace5381e4189c75fcaa6a63a3739026) # Gemma2b-v1.0-sft This model is a fine-tuned version of [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it) on an unknown dataset. ## 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: 5e-06 - 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 - lr_scheduler_warmup_ratio: 0.2 - num_epochs: 1 ### Framework versions - Transformers 4.48.3 - Pytorch 2.5.1+cu124 - Datasets 3.2.0 - Tokenizers 0.21.0