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

# mistral_instruct

This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.1539

## 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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 1.621         | 1.0   | 102  | 1.4441          |
| 1.3795        | 2.0   | 204  | 1.3877          |
| 1.1377        | 3.0   | 306  | 1.3730          |
| 0.877         | 4.0   | 408  | 1.3983          |
| 0.6379        | 5.0   | 510  | 1.4731          |
| 0.4464        | 6.0   | 612  | 1.5966          |
| 0.3066        | 7.0   | 714  | 1.7195          |
| 0.2135        | 8.0   | 816  | 1.8925          |
| 0.1534        | 9.0   | 918  | 2.0300          |
| 0.1169        | 10.0  | 1020 | 2.1539          |


### Framework versions

- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2