--- 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-v0.0-k0 results: [] --- # ribesstefano/RuleBert-v0.0-k0 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: 0.3777 - F1: 0.5004 - Roc Auc: 0.6722 - Accuracy: 0.0375 ## 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-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - training_steps: 500 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:| | 0.3811 | 0.88 | 50 | 0.3716 | 0.4904 | 0.6685 | 0.0583 | | 0.3257 | 1.77 | 100 | 0.3708 | 0.4953 | 0.6701 | 0.0583 | | 0.3178 | 2.65 | 150 | 0.3745 | 0.4977 | 0.6712 | 0.0417 | | 0.3091 | 3.54 | 200 | 0.3750 | 0.4989 | 0.6719 | 0.0417 | | 0.3115 | 4.42 | 250 | 0.3768 | 0.5007 | 0.6724 | 0.0417 | | 0.3092 | 5.31 | 300 | 0.3762 | 0.5021 | 0.6727 | 0.0458 | | 0.3057 | 6.19 | 350 | 0.3772 | 0.5005 | 0.6723 | 0.0375 | | 0.3062 | 7.08 | 400 | 0.3777 | 0.5002 | 0.6721 | 0.0417 | | 0.3086 | 7.96 | 450 | 0.3777 | 0.5005 | 0.6723 | 0.0417 | | 0.3075 | 8.85 | 500 | 0.3777 | 0.5004 | 0.6722 | 0.0375 | ### Framework versions - Transformers 4.36.2 - Pytorch 2.1.0+cu121 - Datasets 2.16.1 - Tokenizers 0.15.0