| --- |
| license: apache-2.0 |
| library_name: peft |
| tags: |
| - generated_from_trainer |
| base_model: mistralai/Mistral-7B-Instruct-v0.2 |
| model-index: |
| - name: andewbot-ft |
| 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. --> |
|
|
| # andewbot-ft |
|
|
| This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.7098 |
|
|
| ## 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: 8 |
| - eval_batch_size: 8 |
| - seed: 42 |
| - gradient_accumulation_steps: 4 |
| - total_train_batch_size: 32 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - lr_scheduler_warmup_steps: 2 |
| - num_epochs: 10 |
| - mixed_precision_training: Native AMP |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:-----:|:----:|:---------------:| |
| | 3.4346 | 0.95 | 10 | 2.3739 | |
| | 1.5612 | 2.0 | 21 | 1.0105 | |
| | 0.9258 | 2.95 | 31 | 0.8001 | |
| | 0.7463 | 4.0 | 42 | 0.7465 | |
| | 0.7622 | 4.95 | 52 | 0.7183 | |
| | 0.6714 | 6.0 | 63 | 0.7132 | |
| | 0.7291 | 6.95 | 73 | 0.7120 | |
| | 0.6559 | 8.0 | 84 | 0.7102 | |
| | 0.7171 | 8.95 | 94 | 0.7099 | |
| | 0.621 | 9.52 | 100 | 0.7098 | |
|
|
|
|
| ### Framework versions |
|
|
| - PEFT 0.8.2 |
| - Transformers 4.39.1 |
| - Pytorch 2.2.0+cu121 |
| - Datasets 2.17.1 |
| - Tokenizers 0.15.2 |
