<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
xlm-roberta-base-WNUT-ner
This model is a fine-tuned version of xlm-roberta-base on the wnut_17 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3376
- Precision: 0.6252
- Recall: 0.4791
- F1: 0.5425
- Accuracy: 0.9523
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: 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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 213 | 0.2787 | 0.5650 | 0.3383 | 0.4232 | 0.9418 |
| No log | 2.0 | 426 | 0.2535 | 0.6225 | 0.4004 | 0.4873 | 0.9485 |
| 0.177 | 3.0 | 639 | 0.2773 | 0.6594 | 0.3911 | 0.4910 | 0.9497 |
| 0.177 | 4.0 | 852 | 0.2651 | 0.6098 | 0.4708 | 0.5314 | 0.9526 |
| 0.0551 | 5.0 | 1065 | 0.3076 | 0.6026 | 0.4652 | 0.5251 | 0.9514 |
| 0.0551 | 6.0 | 1278 | 0.3031 | 0.6343 | 0.4662 | 0.5374 | 0.9531 |
| 0.0551 | 7.0 | 1491 | 0.3319 | 0.6336 | 0.4680 | 0.5384 | 0.9523 |
| 0.0276 | 8.0 | 1704 | 0.3430 | 0.6508 | 0.4560 | 0.5362 | 0.9526 |
| 0.0276 | 9.0 | 1917 | 0.3342 | 0.6138 | 0.4773 | 0.5370 | 0.9521 |
| 0.0157 | 10.0 | 2130 | 0.3376 | 0.6252 | 0.4791 | 0.5425 | 0.9523 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu117
- Datasets 2.9.0
- Tokenizers 0.13.2
