| --- |
| license: apache-2.0 |
| library_name: peft |
| tags: |
| - generated_from_trainer |
| base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ |
| model-index: |
| - name: printinx-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. --> |
|
|
| # printinx-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: 3.1872 |
|
|
| ## 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 | |
| |:-------------:|:-----:|:----:|:---------------:| |
| | 6.0824 | 0.67 | 1 | 3.2835 | |
| | 2.933 | 2.0 | 3 | 3.2615 | |
| | 5.8899 | 2.67 | 4 | 3.2449 | |
| | 2.8651 | 4.0 | 6 | 3.2135 | |
| | 5.4133 | 4.67 | 7 | 3.2023 | |
| | 2.8622 | 6.0 | 9 | 3.1931 | |
| | 4.0023 | 6.67 | 10 | 3.1872 | |
|
|
|
|
| ### Framework versions |
|
|
| - PEFT 0.9.0 |
| - Transformers 4.38.2 |
| - Pytorch 2.1.0+cu121 |
| - Datasets 2.18.0 |
| - Tokenizers 0.15.2 |
