bert-fineturned-ner
This model is a fine-tuned version of bert-base-cased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0626
- Precision: 0.9380
- Recall: 0.9520
- F1: 0.9450
- Accuracy: 0.9870
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.0443 | 1.0 | 878 | 0.0620 | 0.9186 | 0.9399 | 0.9291 | 0.9844 |
0.0275 | 2.0 | 1756 | 0.0629 | 0.9307 | 0.9472 | 0.9389 | 0.9863 |
0.0129 | 3.0 | 2634 | 0.0626 | 0.9380 | 0.9520 | 0.9450 | 0.9870 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 108
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for gkteco/bert-fineturned-ner
Base model
google-bert/bert-base-casedDataset used to train gkteco/bert-fineturned-ner
Evaluation results
- Precision on conll2003self-reported0.938
- Recall on conll2003self-reported0.952
- F1 on conll2003self-reported0.945
- Accuracy on conll2003self-reported0.987