|
|
--- |
|
|
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-k4 |
|
|
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-k4 |
|
|
|
|
|
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: 0.3547 |
|
|
- F1: 0.4940 |
|
|
- Roc Auc: 0.6712 |
|
|
- 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 | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:| |
|
|
| 0.3524 | 0.14 | 250 | 0.3526 | 0.4888 | 0.6731 | 0.0 | |
|
|
| 0.3318 | 0.27 | 500 | 0.3489 | 0.4885 | 0.6698 | 0.0 | |
|
|
| 0.3278 | 0.41 | 750 | 0.3517 | 0.4870 | 0.6709 | 0.0 | |
|
|
| 0.3165 | 0.54 | 1000 | 0.3506 | 0.4953 | 0.6726 | 0.0 | |
|
|
| 0.3243 | 0.68 | 1250 | 0.3501 | 0.4904 | 0.6693 | 0.0 | |
|
|
| 0.3072 | 0.82 | 1500 | 0.3529 | 0.4979 | 0.6715 | 0.0 | |
|
|
| 0.311 | 0.95 | 1750 | 0.3527 | 0.4855 | 0.6664 | 0.0 | |
|
|
| 0.3277 | 1.09 | 2000 | 0.3542 | 0.4900 | 0.6693 | 0.0 | |
|
|
| 0.3102 | 1.22 | 2250 | 0.3535 | 0.4881 | 0.6679 | 0.0 | |
|
|
| 0.3159 | 1.36 | 2500 | 0.3533 | 0.4839 | 0.6663 | 0.0 | |
|
|
| 0.3073 | 1.49 | 2750 | 0.3531 | 0.4994 | 0.6726 | 0.0 | |
|
|
| 0.3108 | 1.63 | 3000 | 0.3542 | 0.4929 | 0.6701 | 0.0 | |
|
|
| 0.3093 | 1.77 | 3250 | 0.3546 | 0.4925 | 0.6702 | 0.0 | |
|
|
| 0.2981 | 1.9 | 3500 | 0.3547 | 0.4933 | 0.6703 | 0.0 | |
|
|
| 0.3046 | 2.04 | 3750 | 0.3547 | 0.4929 | 0.6707 | 0.0 | |
|
|
| 0.3085 | 2.17 | 4000 | 0.3547 | 0.4940 | 0.6712 | 0.0 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.36.2 |
|
|
- Pytorch 2.1.0+cu121 |
|
|
- Datasets 2.16.1 |
|
|
- Tokenizers 0.15.0 |
|
|
|
