<!-- 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. -->
bioBERT-NER-NCBI_disease
This model is a fine-tuned version of dmis-lab/biobert-base-cased-v1.2 on the ncbi_disease dataset. It achieves the following results on the evaluation set:
- Loss: 0.0598
- Precision: 0.8136
- Recall: 0.8653
- F1: 0.8387
- Accuracy: 0.9850
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: 8
- eval_batch_size: 8
- 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 |
---|---|---|---|---|---|---|---|
0.0972 | 1.0 | 680 | 0.0688 | 0.7435 | 0.7624 | 0.7528 | 0.9794 |
0.0397 | 2.0 | 1360 | 0.0508 | 0.7952 | 0.8780 | 0.8345 | 0.9840 |
0.0118 | 3.0 | 2040 | 0.0598 | 0.8136 | 0.8653 | 0.8387 | 0.9850 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 1.18.4
- Tokenizers 0.11.6