distilbert-base-cased-finetuned-nalllabel
This model is a fine-tuned version of distilbert-base-cased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1160
- Precision: 0.8853
- Recall: 0.8977
- F1: 0.8914
- Accuracy: 0.9789
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: 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 |
|---|---|---|---|---|---|---|---|
| 0.1718 | 1.0 | 878 | 0.1071 | 0.8917 | 0.8823 | 0.8870 | 0.9768 |
| 0.0408 | 2.0 | 1756 | 0.1176 | 0.8776 | 0.8973 | 0.8873 | 0.9773 |
| 0.0212 | 3.0 | 2634 | 0.1160 | 0.8853 | 0.8977 | 0.8914 | 0.9789 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2