xlm-roberta-base-finetuned-lener_br-finetuned-lener-br
This model is a fine-tuned version of Luciano/xlm-roberta-base-finetuned-lener_br on the lener_br dataset. It achieves the following results on the evaluation set:
- Loss: nan
- Precision: 0.9206
- Recall: 0.9294
- F1: 0.9250
- Accuracy: 0.9833
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: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0657 | 1.0 | 1957 | nan | 0.7780 | 0.8687 | 0.8209 | 0.9718 |
| 0.0321 | 2.0 | 3914 | nan | 0.8755 | 0.8708 | 0.8731 | 0.9793 |
| 0.0274 | 3.0 | 5871 | nan | 0.8096 | 0.9124 | 0.8579 | 0.9735 |
| 0.0216 | 4.0 | 7828 | nan | 0.7913 | 0.8842 | 0.8352 | 0.9718 |
| 0.0175 | 5.0 | 9785 | nan | 0.7735 | 0.9248 | 0.8424 | 0.9721 |
| 0.0117 | 6.0 | 11742 | nan | 0.9206 | 0.9294 | 0.9250 | 0.9833 |
| 0.0121 | 7.0 | 13699 | nan | 0.8988 | 0.9318 | 0.9150 | 0.9819 |
| 0.0086 | 8.0 | 15656 | nan | 0.8922 | 0.9175 | 0.9047 | 0.9801 |
| 0.007 | 9.0 | 17613 | nan | 0.8482 | 0.8997 | 0.8732 | 0.9769 |
| 0.0051 | 10.0 | 19570 | nan | 0.8730 | 0.9274 | 0.8994 | 0.9798 |
| 0.0045 | 11.0 | 21527 | nan | 0.9172 | 0.9051 | 0.9111 | 0.9819 |
| 0.0014 | 12.0 | 23484 | nan | 0.9138 | 0.9155 | 0.9147 | 0.9823 |
| 0.0029 | 13.0 | 25441 | nan | 0.9099 | 0.9287 | 0.9192 | 0.9834 |
| 0.0035 | 14.0 | 27398 | nan | 0.9019 | 0.9294 | 0.9155 | 0.9831 |
| 0.0005 | 15.0 | 29355 | nan | 0.8886 | 0.9343 | 0.9109 | 0.9825 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1