---
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: mistralai/Mixtral-8x7B-v0.1
model-index:
- name: Mixtral_Alpace_v3
  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. -->

# Mixtral_Alpace_v3

This model is a fine-tuned version of [mistralai/Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8576

## 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: 2.5e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.03
- training_steps: 100

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.1699        | 0.03  | 10   | 1.1218          |
| 1.0878        | 0.07  | 20   | 1.0544          |
| 1.0525        | 0.1   | 30   | 0.9935          |
| 0.9611        | 0.13  | 40   | 0.9529          |
| 0.931         | 0.16  | 50   | 0.9230          |
| 0.9212        | 0.2   | 60   | 0.8993          |
| 0.8918        | 0.23  | 70   | 0.8817          |
| 0.8808        | 0.26  | 80   | 0.8683          |
| 0.8575        | 0.3   | 90   | 0.8604          |
| 0.8848        | 0.33  | 100  | 0.8576          |


### Framework versions

- PEFT 0.9.1.dev0
- Transformers 4.36.0
- Pytorch 2.0.1+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2