---
license: mit
base_model: papluca/xlm-roberta-base-language-detection
tags:
- Italian
- legal ruling
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: ribesstefano/RuleBert-v0.4-k1
  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. -->

# ribesstefano/RuleBert-v0.4-k1

This model is a fine-tuned version of [papluca/xlm-roberta-base-language-detection](https://huggingface.co/papluca/xlm-roberta-base-language-detection) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3335
- F1: 0.5287
- Roc Auc: 0.7065
- Accuracy: 0.0

## 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: 0.0005
- train_batch_size: 4
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 4000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
| 0.3599        | 0.13  | 250  | 0.3361          | 0.5157 | 0.6901  | 0.0      |
| 0.3426        | 0.25  | 500  | 0.3436          | 0.5031 | 0.6842  | 0.0667   |
| 0.3621        | 0.38  | 750  | 0.3340          | 0.4861 | 0.6679  | 0.0      |
| 0.3692        | 0.5   | 1000 | 0.3397          | 0.5409 | 0.7020  | 0.0      |
| 0.3485        | 0.63  | 1250 | 0.3318          | 0.4861 | 0.6679  | 0.0      |
| 0.3494        | 0.75  | 1500 | 0.3306          | 0.4861 | 0.6679  | 0.0      |
| 0.3464        | 0.88  | 1750 | 0.3353          | 0.4861 | 0.6679  | 0.0      |
| 0.3554        | 1.0   | 2000 | 0.3395          | 0.5632 | 0.7243  | 0.0      |
| 0.3509        | 1.13  | 2250 | 0.3303          | 0.4861 | 0.6679  | 0.0      |
| 0.3331        | 1.26  | 2500 | 0.3359          | 0.5302 | 0.6945  | 0.0      |
| 0.3373        | 1.38  | 2750 | 0.3334          | 0.4861 | 0.6679  | 0.0      |
| 0.3416        | 1.51  | 3000 | 0.3355          | 0.4861 | 0.6679  | 0.0      |
| 0.3492        | 1.63  | 3250 | 0.3335          | 0.5287 | 0.7065  | 0.0      |


### Framework versions

- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0