---
library_name: peft
license: other
base_model: mistralai/Ministral-8B-Instruct-2410
tags:
- generated_from_trainer
model-index:
- name: Mistral-8B-Instruct-2410-2025-II
  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-8B-Instruct-2410-2025-II

This model is a fine-tuned version of [mistralai/Ministral-8B-Instruct-2410](https://huggingface.co/mistralai/Ministral-8B-Instruct-2410) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5701

## 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: 2e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.3018        | 0.8658 | 100  | 1.3113          |
| 1.1356        | 1.7273 | 200  | 1.1116          |
| 0.9729        | 2.5887 | 300  | 0.9593          |
| 0.7977        | 3.4502 | 400  | 0.8432          |
| 0.7237        | 4.3117 | 500  | 0.7587          |
| 0.6048        | 5.1732 | 600  | 0.6926          |
| 0.6142        | 6.0346 | 700  | 0.6468          |
| 0.5462        | 6.9004 | 800  | 0.6196          |
| 0.5386        | 7.7619 | 900  | 0.5937          |
| 0.5375        | 8.6234 | 1000 | 0.5801          |
| 0.4623        | 9.4848 | 1100 | 0.5701          |


### Framework versions

- PEFT 0.8.2
- Transformers 4.57.1
- Pytorch 2.7.1+cu118
- Datasets 4.2.0
- Tokenizers 0.22.1