ner-model
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1736
- Precision: 0.8811
- Recall: 0.8919
- F1: 0.8865
- Accuracy: 0.9570
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH 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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1329 | 1.0 | 2250 | 0.2016 | 0.8559 | 0.8541 | 0.8550 | 0.9467 |
| 0.1099 | 2.0 | 4500 | 0.1742 | 0.8626 | 0.8850 | 0.8736 | 0.9537 |
| 0.072 | 3.0 | 6750 | 0.1736 | 0.8811 | 0.8919 | 0.8865 | 0.9570 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.3.0+cu121
- Datasets 5.0.1
- Tokenizers 0.20.3