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

# flippa-v0

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: 0.3732

## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 0.7166        | 0.96  | 6    | 0.6408          |
| 0.633         | 1.92  | 12   | 0.5777          |
| 0.5688        | 2.88  | 18   | 0.5266          |
| 0.4524        | 4.0   | 25   | 0.4774          |
| 0.4781        | 4.96  | 31   | 0.4454          |
| 0.4538        | 5.92  | 37   | 0.4199          |
| 0.4233        | 6.88  | 43   | 0.3991          |
| 0.34          | 8.0   | 50   | 0.3829          |
| 0.3881        | 8.96  | 56   | 0.3750          |
| 0.3169        | 9.6   | 60   | 0.3732          |


### Framework versions

- PEFT 0.9.0
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2