distilbert-base-uncased-finetuned-ner
This model is a fine-tuned version of Jing1113/distilbert-base-uncased-finetuned-srl on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0986
- Precision: 0.8664
- Recall: 0.8732
- F1: 0.8698
- Accuracy: 0.9737
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 |
|---|---|---|---|---|---|---|---|
| 0.0566 | 1.0 | 2531 | 0.0963 | 0.8531 | 0.8727 | 0.8628 | 0.9720 |
| 0.0464 | 2.0 | 5062 | 0.0956 | 0.8591 | 0.8735 | 0.8662 | 0.9729 |
| 0.0389 | 3.0 | 7593 | 0.0986 | 0.8664 | 0.8732 | 0.8698 | 0.9737 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.14.1