README.md

---
license: apache-2.0
base_model: mistralai/Mistral-7B-Instruct-v0.2
tags:
- generated_from_trainer
model-index:
- name: Mistral-7B-Instruct-v0.2-absa-restaurants
  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-7B-Instruct-v0.2-absa-restaurants

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: 0.0280

## 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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- training_steps: 400
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.1197        | 0.36  | 40   | 0.1714          |
| 0.0686        | 0.72  | 80   | 0.0364          |
| 0.0294        | 1.08  | 120  | 0.0321          |
| 0.024         | 1.44  | 160  | 0.0312          |
| 0.0231        | 1.8   | 200  | 0.0279          |
| 0.0183        | 2.16  | 240  | 0.0284          |
| 0.0163        | 2.52  | 280  | 0.0281          |
| 0.0162        | 2.88  | 320  | 0.0273          |
| 0.0153        | 3.24  | 360  | 0.0271          |
| 0.0116        | 3.6   | 400  | 0.0280          |


### Framework versions

- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2