<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
distilbert-base-uncased-finetuned-ner-nlp
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0812
- Precision: 0.8835
- Recall: 0.9039
- F1: 0.8936
- Accuracy: 0.9804
Model description
Essential info about tagged entities
- geo: Geographical Entity
- gpe: Geopolitical Entity
- tim: Time Indicator
Label description
- Label 0: 'B-geo',
- Label 1: 'B-gpe',
- Label 2: 'B-tim',
- Label 3: 'I-geo',
- Label 4: 'I-gpe',
- Label 5: 'I-tim',
- Label 6: 'O'
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: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.0384 | 1.0 | 1781 | 0.0671 | 0.8770 | 0.9038 | 0.8902 | 0.9799 |
0.0295 | 2.0 | 3562 | 0.0723 | 0.8844 | 0.8989 | 0.8915 | 0.9804 |
0.023 | 3.0 | 5343 | 0.0731 | 0.8787 | 0.9036 | 0.8910 | 0.9800 |
0.0186 | 4.0 | 7124 | 0.0812 | 0.8835 | 0.9039 | 0.8936 | 0.9804 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.0
- Tokenizers 0.13.2