---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: mistralai/Mistral-7B-v0.1
model-index:
- name: fine-tuned_mistral
  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. -->

# fine-tuned_mistral

This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1409

## 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: 6
- total_train_batch_size: 24
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.01
- training_steps: 100

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| No log        | 0.0244 | 10   | 1.1972          |
| No log        | 0.0487 | 20   | 1.1709          |
| 1.1921        | 0.0731 | 30   | 1.1592          |
| 1.1921        | 0.0975 | 40   | 1.1548          |
| 1.1255        | 0.1219 | 50   | 1.1526          |
| 1.1255        | 0.1462 | 60   | 1.1487          |
| 1.1255        | 0.1706 | 70   | 1.1478          |
| 1.1164        | 0.1950 | 80   | 1.1452          |
| 1.1164        | 0.2193 | 90   | 1.1427          |
| 1.1271        | 0.2437 | 100  | 1.1409          |


### Framework versions

- PEFT 0.11.1
- Transformers 4.41.1
- Pytorch 2.2.0
- Datasets 2.19.1
- Tokenizers 0.19.1