metadata
license: cc
base_model: joelniklaus/legal-xlm-roberta-base
tags:
- generated_from_trainer
model-index:
- name: bert-leg-al-corpus
results: []
bert-leg-al-corpus
This model is a fine-tuned version of joelniklaus/legal-xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6747
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-06
- train_batch_size: 24
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.9151 | 0.6329 | 100 | 1.7846 |
1.9038 | 1.2658 | 200 | 1.7245 |
1.8655 | 1.8987 | 300 | 1.7416 |
1.8712 | 2.5316 | 400 | 1.7254 |
1.8463 | 3.1646 | 500 | 1.7038 |
1.845 | 3.7975 | 600 | 1.6799 |
1.833 | 4.4304 | 700 | 1.6712 |
1.8196 | 5.0633 | 800 | 1.6761 |
1.8104 | 5.6962 | 900 | 1.6445 |
1.8017 | 6.3291 | 1000 | 1.6668 |
1.7986 | 6.9620 | 1100 | 1.6449 |
1.7955 | 7.5949 | 1200 | 1.6463 |
1.8045 | 8.2278 | 1300 | 1.6303 |
1.7817 | 8.8608 | 1400 | 1.6212 |
1.7831 | 9.4937 | 1500 | 1.6477 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1