bert-base-ner-5
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: 1.9119
- Precision: 0.0205
- Recall: 0.0443
- F1: 0.0280
- Accuracy: 0.6152
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use 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 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 3 | 2.0874 | 0.0189 | 0.0873 | 0.0311 | 0.2981 |
| No log | 2.0 | 6 | 1.9620 | 0.0195 | 0.0552 | 0.0288 | 0.5350 |
| No log | 3.0 | 9 | 1.9119 | 0.0205 | 0.0443 | 0.0280 | 0.6152 |
Framework versions
- Transformers 4.51.2
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1