<!-- 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. -->
medlid-bySent-biobert
This model is a fine-tuned version of dmis-lab/biobert-v1.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1041
- Precision: 0.4663
- Recall: 0.4945
- F1: 0.48
- Accuracy: 0.9758
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: 6
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 381 | 0.0844 | 0.3729 | 0.2473 | 0.2974 | 0.9712 |
0.1204 | 2.0 | 762 | 0.0798 | 0.4854 | 0.2747 | 0.3509 | 0.9735 |
0.0609 | 3.0 | 1143 | 0.0750 | 0.4733 | 0.3901 | 0.4277 | 0.9761 |
0.0356 | 4.0 | 1524 | 0.0859 | 0.4222 | 0.5018 | 0.4586 | 0.9736 |
0.0356 | 5.0 | 1905 | 0.0941 | 0.4795 | 0.4487 | 0.4636 | 0.9768 |
0.0188 | 6.0 | 2286 | 0.1041 | 0.4663 | 0.4945 | 0.48 | 0.9758 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.11.0
- Datasets 2.13.1
- Tokenizers 0.13.3