distilbert-base-uncased-finetuned-ner
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1660
- Precision: 0.9701
- Recall: 0.9679
- F1: 0.9690
- Accuracy: 0.9863
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: 11
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0091 | 1.0 | 5372 | 0.1034 | 0.9693 | 0.9649 | 0.9671 | 0.9858 |
| 0.0052 | 2.0 | 10744 | 0.1362 | 0.9715 | 0.9679 | 0.9697 | 0.9868 |
| 0.0064 | 3.0 | 16116 | 0.1415 | 0.9715 | 0.9657 | 0.9686 | 0.9844 |
| 0.0026 | 4.0 | 21488 | 0.1629 | 0.9709 | 0.9701 | 0.9705 | 0.9870 |
| 0.0034 | 5.0 | 26860 | 0.1345 | 0.9737 | 0.9687 | 0.9712 | 0.9851 |
| 0.0019 | 6.0 | 32232 | 0.1297 | 0.9700 | 0.9649 | 0.9675 | 0.9841 |
| 0.0031 | 7.0 | 37604 | 0.1543 | 0.9716 | 0.9701 | 0.9709 | 0.9868 |
| 0.0021 | 8.0 | 42976 | 0.0605 | 0.9782 | 0.9716 | 0.9749 | 0.9903 |
| 0.0023 | 9.0 | 48348 | 0.1506 | 0.9731 | 0.9701 | 0.9716 | 0.9877 |
| 0.0021 | 10.0 | 53720 | 0.1714 | 0.9693 | 0.9672 | 0.9682 | 0.9860 |
| 0.0015 | 11.0 | 59092 | 0.1660 | 0.9701 | 0.9679 | 0.9690 | 0.9863 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.13.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3