| license: llama2 | |
| library_name: peft | |
| tags: | |
| - generated_from_trainer | |
| base_model: meta-llama/Llama-2-7b-chat-hf | |
| model-index: | |
| - name: Llama-2-7b-chat-hf-finetune-SWE_70_30_EN | |
| 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. --> | |
| # Llama-2-7b-chat-hf-finetune-SWE_70_30_EN | |
| This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on an unknown dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 1.8878 | |
| ## 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: 2 | |
| - eval_batch_size: 2 | |
| - seed: 42 | |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 | |
| - lr_scheduler_type: reduce_lr_on_plateau | |
| - num_epochs: 5 | |
| - mixed_precision_training: Native AMP | |
| ### Training results | |
| | Training Loss | Epoch | Step | Validation Loss | | |
| |:-------------:|:-----:|:----:|:---------------:| | |
| | 1.5964 | 1.0 | 1443 | 1.3030 | | |
| | 0.8889 | 2.0 | 2886 | 1.3256 | | |
| | 0.7563 | 3.0 | 4329 | 1.5178 | | |
| | 0.4312 | 4.0 | 5772 | 1.7452 | | |
| | 0.3434 | 5.0 | 7215 | 1.8878 | | |
| ### Framework versions | |
| - PEFT 0.10.0 | |
| - Transformers 4.40.1 | |
| - Pytorch 2.3.0+cu121 | |
| - Datasets 2.19.0 | |
| - Tokenizers 0.19.1 |