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-v0.5-k3
results: []
ribesstefano/RuleBert-v0.5-k3
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: 0.3277
- F1: 0.4513
- Roc Auc: 0.6511
- Accuracy: 0.0571
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: 5e-06
- train_batch_size: 2
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 8000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.4223 | 0.06 | 250 | 0.3813 | 0.4517 | 0.6511 | 0.0571 |
| 0.3584 | 0.12 | 500 | 0.3377 | 0.4512 | 0.6506 | 0.0714 |
| 0.3591 | 0.18 | 750 | 0.3307 | 0.4507 | 0.6503 | 0.0714 |
| 0.3441 | 0.24 | 1000 | 0.3273 | 0.4515 | 0.6507 | 0.0714 |
| 0.3175 | 0.3 | 1250 | 0.3271 | 0.4507 | 0.6503 | 0.0714 |
| 0.3366 | 0.36 | 1500 | 0.3277 | 0.4513 | 0.6511 | 0.0571 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0