wiki_hu_ner
This model is a fine-tuned version of distilbert-base-uncased on the wikiann dataset. It achieves the following results on the evaluation set:
- Loss: 0.1585
- Precision: 0.8669
- Recall: 0.8782
- F1: 0.8725
- Accuracy: 0.9632
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2429 | 1.0 | 1250 | 0.1849 | 0.8047 | 0.8153 | 0.8100 | 0.9448 |
| 0.1371 | 2.0 | 2500 | 0.1505 | 0.8455 | 0.8577 | 0.8516 | 0.9576 |
| 0.0986 | 3.0 | 3750 | 0.1516 | 0.8520 | 0.8708 | 0.8613 | 0.9603 |
| 0.0695 | 4.0 | 5000 | 0.1500 | 0.8656 | 0.8745 | 0.8700 | 0.9624 |
| 0.0489 | 5.0 | 6250 | 0.1585 | 0.8669 | 0.8782 | 0.8725 | 0.9632 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3