bert-finetuned-chunk
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: 0.1590
- Precision: 0.9222
- Recall: 0.9207
- F1: 0.9214
- Accuracy: 0.9618
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1877 | 1.0 | 1756 | 0.1758 | 0.9134 | 0.9119 | 0.9126 | 0.9575 |
| 0.1275 | 2.0 | 3512 | 0.1591 | 0.9253 | 0.9177 | 0.9215 | 0.9609 |
| 0.0912 | 3.0 | 5268 | 0.1590 | 0.9222 | 0.9207 | 0.9214 | 0.9618 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3