| --- |
| library_name: peft |
| license: llama3.2 |
| base_model: meta-llama/Llama-3.2-1B-Instruct |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: NL2linux |
| 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. --> |
|
|
| # NL2linux |
|
|
| This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on [garavv/NL2linux](https://huggingface.co/datasets/garavv/NL2linux) |
| It achieves the following results on the evaluation set: |
| - Loss: 0.7192 |
|
|
| ## 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-05 |
| - train_batch_size: 16 |
| - eval_batch_size: 16 |
| - seed: 42 |
| - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| - lr_scheduler_type: linear |
| - num_epochs: 3 |
| - mixed_precision_training: Native AMP |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:------:|:----:|:---------------:| |
| | 0.9742 | 0.2817 | 500 | 0.9460 | |
| | 0.8974 | 0.5634 | 1000 | 0.8695 | |
| | 0.8392 | 0.8451 | 1500 | 0.8290 | |
| | 0.7308 | 1.1268 | 2000 | 0.7992 | |
| | 0.7356 | 1.4085 | 2500 | 0.7761 | |
| | 0.7338 | 1.6901 | 3000 | 0.7566 | |
| | 0.705 | 1.9718 | 3500 | 0.7443 | |
| | 0.6469 | 2.2535 | 4000 | 0.7372 | |
| | 0.6197 | 2.5352 | 4500 | 0.7271 | |
| | 0.6438 | 2.8169 | 5000 | 0.7214 | |
|
|
|
|
| ### Framework versions |
|
|
| - PEFT 0.14.0 |
| - Transformers 4.49.0 |
| - Pytorch 2.5.1+cu121 |
| - Datasets 3.3.2 |
| - Tokenizers 0.21.0 |
