metadata
license: mit
base_model: FacebookAI/xlm-roberta-large
tags:
- generated_from_trainer
model-index:
- name: xlm-roberta-large-legal-act
results: []
xlm-roberta-large-legal-act
This model is a fine-tuned version of FacebookAI/xlm-roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2099
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: 1e-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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4944 | 1.0 | 443 | 0.2680 |
| 0.317 | 2.0 | 886 | 0.3006 |
| 0.494 | 3.0 | 1329 | 0.2791 |
| 0.2472 | 4.0 | 1772 | 0.2096 |
| 0.117 | 5.0 | 2215 | 0.1947 |
| 0.0838 | 6.0 | 2658 | 0.1859 |
| 0.2747 | 7.0 | 3101 | 0.2133 |
| 0.2151 | 8.0 | 3544 | 0.1685 |
| 0.0016 | 9.0 | 3987 | 0.1614 |
| 0.0968 | 10.0 | 4430 | 0.2099 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1