huggingface-nlp-bert-finetuned-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: nan
- Precision: 0.0
- Recall: 0.0
- F1: 0.0
- Accuracy: 0.7612
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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 1.0686 | 1.0 | 878 | nan | 0.0 | 0.0 | 0.0 | 0.7612 |
| 0.0 | 2.0 | 1756 | nan | 0.0 | 0.0 | 0.0 | 0.7612 |
| 0.0 | 3.0 | 2634 | nan | 0.0 | 0.0 | 0.0 | 0.7612 |
Framework versions
- Transformers 4.50.0
- Pytorch 2.6.0+rocm6.2.4
- Datasets 3.4.1
- Tokenizers 0.21.1
- Downloads last month
- 3
Model tree for HarryDn/huggingface-nlp-bert-finetuned-ner
Base model
google-bert/bert-base-casedDataset used to train HarryDn/huggingface-nlp-bert-finetuned-ner
Evaluation results
- Precision on conll2003validation set self-reported0.000
- Recall on conll2003validation set self-reported0.000
- F1 on conll2003validation set self-reported0.000
- Accuracy on conll2003validation set self-reported0.761