distilbert-base-cased-finetuned-ner
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: 0.0709
- Precision: 0.9170
- Recall: 0.9272
- F1: 0.9221
- Accuracy: 0.9804
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 |
|---|---|---|---|---|---|---|---|
| 0.2732 | 1.0 | 878 | 0.0916 | 0.8931 | 0.8961 | 0.8946 | 0.9736 |
| 0.0717 | 2.0 | 1756 | 0.0726 | 0.9166 | 0.9212 | 0.9189 | 0.9794 |
| 0.0364 | 3.0 | 2634 | 0.0709 | 0.9170 | 0.9272 | 0.9221 | 0.9804 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.2+cu102
- Datasets 2.0.0
- Tokenizers 0.12.1
- Downloads last month
- 5
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.
Dataset used to train swardiantara/distilbert-base-cased-finetuned-ner
Evaluation results
- Precision on conll2003self-reported0.917
- Recall on conll2003self-reported0.927
- F1 on conll2003self-reported0.922
- Accuracy on conll2003self-reported0.980