abnormality_classifier_biobert_v1
This model is a fine-tuned version of dmis-lab/biobert-v1.1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3132
- Accuracy: 0.957
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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.0733 | 1.0 | 1125 | 0.1607 | 0.947 |
0.1204 | 2.0 | 2250 | 0.1543 | 0.955 |
0.076 | 3.0 | 3375 | 0.1738 | 0.957 |
0.1097 | 4.0 | 4500 | 0.2200 | 0.957 |
0.0651 | 5.0 | 5625 | 0.2456 | 0.957 |
0.0224 | 6.0 | 6750 | 0.2900 | 0.956 |
0.0054 | 7.0 | 7875 | 0.3137 | 0.951 |
0.0075 | 8.0 | 9000 | 0.2893 | 0.957 |
0.0092 | 9.0 | 10125 | 0.3089 | 0.957 |
0.0042 | 10.0 | 11250 | 0.3132 | 0.957 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 5