modello_finetuning1

This model is a fine-tuned version of distilbert-base-multilingual-cased on the swiss_law_area_prediction dataset. It achieves the following results on the evaluation set:

• Loss: 0.0506
• Precision: 0.9922
• Recall: 0.9902
• F1: 0.9911

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: 6e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1
0.0834	0.38	500	0.1812	0.9793	0.9677	0.9730
0.1029	0.76	1000	0.0973	0.9875	0.9834	0.9854
0.0066	1.15	1500	0.0647	0.9864	0.9886	0.9875
0.0008	1.53	2000	0.0619	0.9913	0.9893	0.9902
0.0003	1.91	2500	0.0506	0.9922	0.9902	0.9911

Framework versions

• Transformers 4.36.1
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0