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-k2
results: []
ribesstefano/RuleBert-v0.4-k2
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: 0.3021
- F1: 0.5409
- Roc Auc: 0.6961
- 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 |
|---|---|---|---|---|---|---|
| 0.3653 | 0.12 | 250 | 0.3184 | 0.5103 | 0.6747 | 0.0 |
| 0.3513 | 0.24 | 500 | 0.3022 | 0.5103 | 0.6747 | 0.0 |
| 0.3758 | 0.36 | 750 | 0.2956 | 0.5103 | 0.6747 | 0.0 |
| 0.355 | 0.48 | 1000 | 0.3073 | 0.5409 | 0.6961 | 0.0 |
| 0.3499 | 0.6 | 1250 | 0.3098 | 0.5103 | 0.6747 | 0.0 |
| 0.3484 | 0.72 | 1500 | 0.3009 | 0.5103 | 0.6747 | 0.0 |
| 0.3394 | 0.85 | 1750 | 0.2978 | 0.5103 | 0.6747 | 0.0 |
| 0.3469 | 0.97 | 2000 | 0.2975 | 0.5103 | 0.6747 | 0.0 |
| 0.3522 | 1.09 | 2250 | 0.3021 | 0.5409 | 0.6961 | 0.0 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0