<!-- 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
This model is a fine-tuned version of distilbert-base-uncased on the ncbi_disease dataset. It achieves the following results on the evaluation set:
- Loss: 0.0735
- Precision: 0.8144
- Recall: 0.8605
- F1: 0.8369
- Accuracy: 0.9805
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 |
---|---|---|---|---|---|---|---|
No log | 1.0 | 340 | 0.0761 | 0.7560 | 0.8316 | 0.7920 | 0.9758 |
0.1236 | 2.0 | 680 | 0.0719 | 0.8105 | 0.8355 | 0.8228 | 0.9794 |
0.0397 | 3.0 | 1020 | 0.0735 | 0.8144 | 0.8605 | 0.8369 | 0.9805 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.2