| | --- |
| | license: gemma |
| | library_name: peft |
| | tags: |
| | - trl |
| | - sft |
| | - generated_from_trainer |
| | base_model: google/gemma-2b |
| | model-index: |
| | - name: gemma2b_quotes |
| | results: [] |
| | --- |
| | |
| | <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| | should probably proofread and complete it, then remove this comment. --> |
| |
|
| | # gemma2b_quotes |
| | |
| | This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 2.7806 |
| | |
| | ## 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: 0.0002 |
| | - train_batch_size: 1 |
| | - eval_batch_size: 8 |
| | - seed: 42 |
| | - gradient_accumulation_steps: 4 |
| | - total_train_batch_size: 4 |
| | - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| | - lr_scheduler_type: constant |
| | - lr_scheduler_warmup_steps: 0.03 |
| | - training_steps: 50 |
| | - mixed_precision_training: Native AMP |
| | |
| | ### Training results |
| | |
| | | Training Loss | Epoch | Step | Validation Loss | |
| | |:-------------:|:------:|:----:|:---------------:| |
| | | 2.38 | 0.0199 | 10 | 2.9476 | |
| | | 2.0109 | 0.0399 | 20 | 2.9249 | |
| | | 2.1081 | 0.0598 | 30 | 2.8474 | |
| | | 1.5517 | 0.0798 | 40 | 2.7603 | |
| | | 2.1219 | 0.0997 | 50 | 2.7806 | |
| | |
| | |
| | ### Framework versions |
| | |
| | - PEFT 0.11.1 |
| | - Transformers 4.41.2 |
| | - Pytorch 2.3.0+cu121 |
| | - Datasets 2.20.0 |
| | - Tokenizers 0.19.1 |
