---
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
library_name: peft
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: shawgpt-ft-rank15
  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-ft-rank15

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: 1.5116

## 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: 12
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss |
|:-------------:|:-------:|:----:|:---------------:|
| 1.0283        | 0.9231  | 3    | 1.3097          |
| 0.9868        | 1.8462  | 6    | 1.3728          |
| 0.9174        | 2.7692  | 9    | 1.3527          |
| 0.6429        | 4.0     | 13   | 1.4026          |
| 0.8442        | 4.9231  | 16   | 1.4004          |
| 0.7766        | 5.8462  | 19   | 1.4248          |
| 0.7289        | 6.7692  | 22   | 1.4474          |
| 0.543         | 8.0     | 26   | 1.4707          |
| 0.6976        | 8.9231  | 29   | 1.4967          |
| 0.6682        | 9.8462  | 32   | 1.5151          |
| 0.6726        | 10.7692 | 35   | 1.5118          |
| 0.1014        | 11.0769 | 36   | 1.5116          |


### Framework versions

- PEFT 0.13.2
- Transformers 4.44.2
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.19.1