| --- |
| base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ |
| library_name: peft |
| license: apache-2.0 |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: MBGPT-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. --> |
|
|
| # MBGPT-ft |
|
|
| This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 1.8936 |
|
|
| ## 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: 4 |
| - eval_batch_size: 4 |
| - seed: 42 |
| - gradient_accumulation_steps: 4 |
| - total_train_batch_size: 16 |
| - 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 | |
| |:-------------:|:------:|:----:|:---------------:| |
| | 4.5929 | 0.9231 | 3 | 3.9618 | |
| | 4.0418 | 1.8462 | 6 | 3.4346 | |
| | 3.4614 | 2.7692 | 9 | 2.9810 | |
| | 2.253 | 4.0 | 13 | 2.5605 | |
| | 2.666 | 4.9231 | 16 | 2.3088 | |
| | 2.3577 | 5.8462 | 19 | 2.1243 | |
| | 2.1787 | 6.7692 | 22 | 2.0194 | |
| | 1.5374 | 8.0 | 26 | 1.9470 | |
| | 2.0037 | 8.9231 | 29 | 1.9060 | |
| | 1.3905 | 9.2308 | 30 | 1.8936 | |
|
|
|
|
| ### Framework versions |
|
|
| - PEFT 0.12.0 |
| - Transformers 4.42.4 |
| - Pytorch 2.1.0+cu121 |
| - Datasets 2.20.0 |
| - Tokenizers 0.19.1 |
