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

# working

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: 1.0615

## 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: 5
- eval_batch_size: 5
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 20
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 50
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.2856        | 1.0   | 2    | 1.9140          |
| 2.2072        | 2.0   | 4    | 1.7495          |
| 1.9669        | 3.0   | 6    | 1.5863          |
| 1.7392        | 4.0   | 8    | 1.4619          |
| 1.5773        | 5.0   | 10   | 1.3566          |
| 1.4356        | 6.0   | 12   | 1.2507          |
| 1.2947        | 7.0   | 14   | 1.1430          |
| 1.1322        | 8.0   | 16   | 1.0251          |
| 0.9668        | 9.0   | 18   | 0.9297          |
| 0.8458        | 10.0  | 20   | 0.8683          |
| 0.7633        | 11.0  | 22   | 0.8292          |
| 0.715         | 12.0  | 24   | 0.8035          |
| 0.6751        | 13.0  | 26   | 0.7806          |
| 0.6393        | 14.0  | 28   | 0.7605          |
| 0.6037        | 15.0  | 30   | 0.7473          |
| 0.5686        | 16.0  | 32   | 0.7427          |
| 0.5395        | 17.0  | 34   | 0.7443          |
| 0.5141        | 18.0  | 36   | 0.7448          |
| 0.4879        | 19.0  | 38   | 0.7412          |
| 0.4615        | 20.0  | 40   | 0.7433          |
| 0.4394        | 21.0  | 42   | 0.7501          |
| 0.4136        | 22.0  | 44   | 0.7589          |
| 0.3913        | 23.0  | 46   | 0.7660          |
| 0.3683        | 24.0  | 48   | 0.7728          |
| 0.3473        | 25.0  | 50   | 0.7873          |
| 0.3273        | 26.0  | 52   | 0.8055          |
| 0.3087        | 27.0  | 54   | 0.8237          |
| 0.2898        | 28.0  | 56   | 0.8365          |
| 0.2717        | 29.0  | 58   | 0.8474          |
| 0.2579        | 30.0  | 60   | 0.8657          |
| 0.2404        | 31.0  | 62   | 0.8871          |
| 0.2278        | 32.0  | 64   | 0.9067          |
| 0.2149        | 33.0  | 66   | 0.9264          |
| 0.2042        | 34.0  | 68   | 0.9430          |
| 0.1949        | 35.0  | 70   | 0.9572          |
| 0.1887        | 36.0  | 72   | 0.9703          |
| 0.1802        | 37.0  | 74   | 0.9840          |
| 0.1737        | 38.0  | 76   | 0.9960          |
| 0.1691        | 39.0  | 78   | 1.0060          |
| 0.1642        | 40.0  | 80   | 1.0152          |
| 0.1613        | 41.0  | 82   | 1.0244          |
| 0.1571        | 42.0  | 84   | 1.0322          |
| 0.1539        | 43.0  | 86   | 1.0395          |
| 0.1522        | 44.0  | 88   | 1.0462          |
| 0.1494        | 45.0  | 90   | 1.0518          |
| 0.1474        | 46.0  | 92   | 1.0556          |
| 0.1469        | 47.0  | 94   | 1.0582          |
| 0.1456        | 48.0  | 96   | 1.0601          |
| 0.1459        | 49.0  | 98   | 1.0612          |
| 0.1438        | 50.0  | 100  | 1.0615          |


### Framework versions

- PEFT 0.9.0
- Transformers 4.38.1
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2