| library_name: peft | |
| tags: | |
| - trl | |
| - sft | |
| - generated_from_trainer | |
| base_model: gizemgg/Llama-2-7b-chat-hf-finetuned-wiki-eng-summary-trial-gen5 | |
| model-index: | |
| - name: results | |
| 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. --> | |
| # results | |
| This model is a fine-tuned version of [gizemgg/Llama-2-7b-chat-hf-finetuned-wiki-eng-summary-trial-gen5](https://huggingface.co/gizemgg/Llama-2-7b-chat-hf-finetuned-wiki-eng-summary-trial-gen5) on an unknown dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 0.8774 | |
| ## 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: 3e-05 | |
| - train_batch_size: 16 | |
| - eval_batch_size: 16 | |
| - seed: 42 | |
| - gradient_accumulation_steps: 16 | |
| - total_train_batch_size: 256 | |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 | |
| - lr_scheduler_type: constant | |
| - lr_scheduler_warmup_ratio: 0.03 | |
| - num_epochs: 5 | |
| ### Training results | |
| | Training Loss | Epoch | Step | Validation Loss | | |
| |:-------------:|:-----:|:----:|:---------------:| | |
| | 1.0487 | 0.93 | 6 | 0.9595 | | |
| | 1.0306 | 1.86 | 12 | 0.9414 | | |
| | 0.8627 | 2.95 | 19 | 0.9183 | | |
| | 0.9787 | 3.88 | 25 | 0.8934 | | |
| | 0.7588 | 4.66 | 30 | 0.8774 | | |
| ### Framework versions | |
| - PEFT 0.8.2 | |
| - Transformers 4.39.3 | |
| - Pytorch 2.1.2+cu121 | |
| - Datasets 2.17.0 | |
| - Tokenizers 0.15.2 |