legal_ner_model
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1039
- Model Preparation Time: 0.0049
- Accuracy: 0.9740
- Precision: 0.9520
- Recall: 0.9430
- F1: 0.9475
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|---|
| 0.1464 | 1.0 | 1375 | 0.1224 | 0.0049 | 0.9647 | 0.9364 | 0.9204 | 0.9284 |
| 0.0969 | 2.0 | 2750 | 0.1027 | 0.0049 | 0.9723 | 0.9523 | 0.9355 | 0.9438 |
| 0.0814 | 3.0 | 4125 | 0.1039 | 0.0049 | 0.9740 | 0.9520 | 0.9430 | 0.9475 |
Framework versions
- Transformers 4.55.4
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.21.4