metadata
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-k0
results: []
ribesstefano/RuleBert-v0.4-k0
This model is a fine-tuned version of papluca/xlm-roberta-base-language-detection on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3888
- F1: 0.4972
- Roc Auc: 0.6720
- 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 |
|---|---|---|---|---|---|---|
| 0.3397 | 0.12 | 250 | 0.3972 | 0.5304 | 0.6872 | 0.0 |
| 0.3442 | 0.25 | 500 | 0.3797 | 0.5181 | 0.6758 | 0.0667 |
| 0.3373 | 0.37 | 750 | 0.3896 | 0.4972 | 0.6720 | 0.0 |
| 0.3366 | 0.49 | 1000 | 0.3829 | 0.5176 | 0.6763 | 0.04 |
| 0.326 | 0.62 | 1250 | 0.3776 | 0.4972 | 0.6720 | 0.0 |
| 0.354 | 0.74 | 1500 | 0.3888 | 0.4972 | 0.6720 | 0.0 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0