--- base_model: google/gemma-2-2b-it library_name: peft license: gemma tags: - trl - sft - generated_from_trainer model-index: - name: Gemma-2-2B_task-1_60-samples_config-1_auto results: [] --- # Gemma-2-2B_task-1_60-samples_config-1_auto 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. It achieves the following results on the evaluation set: - Loss: 2.3285 ## 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: 0.0001 - train_batch_size: 1 - eval_batch_size: 1 - seed: 42 - distributed_type: multi-GPU - gradient_accumulation_steps: 8 - total_train_batch_size: 8 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-------:|:----:|:---------------:| | 1.5831 | 0.8696 | 5 | 1.5868 | | 1.4338 | 1.9130 | 11 | 1.2779 | | 1.0588 | 2.9565 | 17 | 1.0678 | | 0.9374 | 4.0 | 23 | 1.0078 | | 0.7559 | 4.8696 | 28 | 0.9772 | | 0.6571 | 5.9130 | 34 | 0.9865 | | 0.4598 | 6.9565 | 40 | 1.0228 | | 0.3646 | 8.0 | 46 | 1.1915 | | 0.2273 | 8.8696 | 51 | 1.4645 | | 0.1298 | 9.9130 | 57 | 1.8402 | | 0.0881 | 10.9565 | 63 | 2.1073 | | 0.0555 | 12.0 | 69 | 2.3285 | ### Framework versions - PEFT 0.12.0 - Transformers 4.44.0 - Pytorch 2.1.2+cu121 - Datasets 2.20.0 - Tokenizers 0.19.1