README.md

metadata

license: cc
base_model: joelniklaus/legal-swiss-roberta-large
tags:
  - generated_from_trainer
datasets:
  - swiss_judgment_prediction
metrics:
  - accuracy
model-index:
  - name: fine_tuned_model_on_SJP_dataset_it_balanced_2048_tokens
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: swiss_judgment_prediction
          type: swiss_judgment_prediction
          config: it
          split: test
          args: it
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8177339901477833

fine_tuned_model_on_SJP_dataset_it_balanced_2048_tokens

This model is a fine-tuned version of joelniklaus/legal-swiss-roberta-large on the swiss_judgment_prediction dataset. It achieves the following results on the evaluation set:

• Loss: 0.7964
• Accuracy: 0.8177

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: 4
• 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	Accuracy
0.7513	1.0	768	0.6783	0.7956
0.6008	2.0	1536	0.7964	0.8177

Framework versions

• Transformers 4.37.2
• Pytorch 2.2.0+cu118
• Datasets 2.17.0
• Tokenizers 0.15.1