| --- |
| license: mit |
| base_model: classla/xlm-roberta-base-multilingual-text-genre-classifier |
| tags: |
| - Italian |
| - legal ruling |
| - generated_from_trainer |
| metrics: |
| - f1 |
| - accuracy |
| model-index: |
| - name: ribesstefano/RuleBert-v0.1-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-v0.1-k1 |
|
|
| This model is a fine-tuned version of [classla/xlm-roberta-base-multilingual-text-genre-classifier](https://huggingface.co/classla/xlm-roberta-base-multilingual-text-genre-classifier) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.3207 |
| - F1: 0.4762 |
| - Roc Auc: 0.6657 |
| - 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: 2e-05 |
| - 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 | |
| |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:| |
| | 0.3316 | 0.14 | 250 | 0.3375 | 0.4771 | 0.6730 | 0.0 | |
| | 0.3343 | 0.28 | 500 | 0.3277 | 0.4724 | 0.6700 | 0.0 | |
| | 0.3328 | 0.41 | 750 | 0.3235 | 0.4624 | 0.6623 | 0.0 | |
| | 0.3365 | 0.55 | 1000 | 0.3227 | 0.4663 | 0.6635 | 0.0 | |
| | 0.3257 | 0.69 | 1250 | 0.3236 | 0.4669 | 0.6633 | 0.0 | |
| | 0.3194 | 0.83 | 1500 | 0.3243 | 0.4912 | 0.6768 | 0.0 | |
| | 0.3232 | 0.97 | 1750 | 0.3223 | 0.4714 | 0.6645 | 0.0 | |
| | 0.3151 | 1.11 | 2000 | 0.3216 | 0.4727 | 0.6650 | 0.0 | |
| | 0.3229 | 1.24 | 2250 | 0.3217 | 0.4756 | 0.6665 | 0.0 | |
| | 0.323 | 1.38 | 2500 | 0.3237 | 0.4736 | 0.6651 | 0.0 | |
| | 0.3175 | 1.52 | 2750 | 0.3222 | 0.4731 | 0.6647 | 0.0 | |
| | 0.3133 | 1.66 | 3000 | 0.3203 | 0.4739 | 0.6651 | 0.0 | |
| | 0.3089 | 1.8 | 3250 | 0.3205 | 0.4751 | 0.6654 | 0.0 | |
| | 0.3285 | 1.94 | 3500 | 0.3208 | 0.4759 | 0.6657 | 0.0 | |
| | 0.3119 | 2.07 | 3750 | 0.3207 | 0.4768 | 0.6660 | 0.0 | |
| | 0.3169 | 2.21 | 4000 | 0.3207 | 0.4762 | 0.6657 | 0.0 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.36.2 |
| - Pytorch 2.1.0+cu121 |
| - Datasets 2.16.1 |
| - Tokenizers 0.15.0 |
|
|
