bert-finetuned-ner-cti
This model is a fine-tuned version of bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1001
- Precision: 0.9730
- Recall: 0.9844
- F1: 0.9787
- Accuracy: 0.9852
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: 8
- eval_batch_size: 8
- 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 |
|---|---|---|---|---|---|---|---|
| 0.0346 | 1.0 | 1725 | 0.0779 | 0.9603 | 0.9788 | 0.9695 | 0.9812 |
| 0.0271 | 2.0 | 3450 | 0.0840 | 0.9588 | 0.9811 | 0.9698 | 0.9815 |
| 0.026 | 3.0 | 5175 | 0.0718 | 0.9686 | 0.9812 | 0.9748 | 0.9836 |
| 0.018 | 4.0 | 6900 | 0.0749 | 0.9687 | 0.9828 | 0.9757 | 0.9841 |
| 0.0136 | 5.0 | 8625 | 0.0872 | 0.9702 | 0.9838 | 0.9770 | 0.9847 |
| 0.0085 | 6.0 | 10350 | 0.0932 | 0.9682 | 0.9833 | 0.9757 | 0.9838 |
| 0.0075 | 7.0 | 12075 | 0.0906 | 0.9741 | 0.9836 | 0.9788 | 0.9852 |
| 0.0051 | 8.0 | 13800 | 0.0951 | 0.9727 | 0.9836 | 0.9781 | 0.9849 |
| 0.0034 | 9.0 | 15525 | 0.0990 | 0.9732 | 0.9846 | 0.9789 | 0.9851 |
| 0.0027 | 10.0 | 17250 | 0.1001 | 0.9730 | 0.9844 | 0.9787 | 0.9852 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 16
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for thongnef/bert-finetuned-ner-cti
Base model
google-bert/bert-base-cased