---
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
library_name: peft
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: shawgpt-ftV
  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. -->

# shawgpt-ftV

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: 1.3077

## 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: 0.00025
- 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: 20
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss |
|:-------------:|:-------:|:----:|:---------------:|
| 4.5767        | 0.9231  | 3    | 3.8886          |
| 3.8938        | 1.8462  | 6    | 3.2231          |
| 3.1768        | 2.7692  | 9    | 2.6739          |
| 1.9525        | 4.0     | 13   | 2.1278          |
| 2.113         | 4.9231  | 16   | 1.7846          |
| 1.6965        | 5.8462  | 19   | 1.5702          |
| 1.4533        | 6.7692  | 22   | 1.4343          |
| 1.0385        | 8.0     | 26   | 1.3727          |
| 1.3349        | 8.9231  | 29   | 1.3505          |
| 1.279         | 9.8462  | 32   | 1.3351          |
| 1.2756        | 10.7692 | 35   | 1.3248          |
| 0.9088        | 12.0    | 39   | 1.3167          |
| 1.2197        | 12.9231 | 42   | 1.3130          |
| 1.1796        | 13.8462 | 45   | 1.3101          |
| 1.1802        | 14.7692 | 48   | 1.3096          |
| 0.8835        | 16.0    | 52   | 1.3088          |
| 1.149         | 16.9231 | 55   | 1.3084          |
| 1.1334        | 17.8462 | 58   | 1.3080          |
| 0.7991        | 18.4615 | 60   | 1.3077          |


### Framework versions

- PEFT 0.13.2
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1