<!-- 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-LitCovid-v1.3.1
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: 0.6731
- Hamming loss: 0.0186
- F1 micro: 0.8434
- F1 macro: 0.3657
- F1 weighted: 0.8790
- F1 samples: 0.8763
- Precision micro: 0.7702
- Precision macro: 0.2942
- Precision weighted: 0.8399
- Precision samples: 0.8618
- Recall micro: 0.9320
- Recall macro: 0.7288
- Recall weighted: 0.9320
- Recall samples: 0.9432
- Roc Auc: 0.9581
- Accuracy: 0.6841
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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Hamming loss | F1 micro | F1 macro | F1 weighted | F1 samples | Precision micro | Precision macro | Precision weighted | Precision samples | Recall micro | Recall macro | Recall weighted | Recall samples | Roc Auc | Accuracy |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
1.1065 | 1.0 | 2272 | 0.4899 | 0.0357 | 0.7347 | 0.2684 | 0.8280 | 0.8274 | 0.6112 | 0.2128 | 0.7700 | 0.7976 | 0.9207 | 0.7424 | 0.9207 | 0.9370 | 0.9437 | 0.5688 |
0.8552 | 2.0 | 4544 | 0.4641 | 0.0246 | 0.8018 | 0.3270 | 0.8588 | 0.8548 | 0.7057 | 0.2595 | 0.8123 | 0.8327 | 0.9282 | 0.7833 | 0.9282 | 0.9424 | 0.9531 | 0.6325 |
0.7061 | 3.0 | 6816 | 0.5058 | 0.0227 | 0.8166 | 0.3320 | 0.8679 | 0.8652 | 0.7201 | 0.2640 | 0.8146 | 0.8402 | 0.9429 | 0.7601 | 0.9429 | 0.9522 | 0.9611 | 0.6548 |
0.5914 | 4.0 | 9088 | 0.6116 | 0.0196 | 0.8368 | 0.3588 | 0.8758 | 0.8719 | 0.7572 | 0.2869 | 0.8321 | 0.8533 | 0.9353 | 0.7398 | 0.9353 | 0.9456 | 0.9591 | 0.6706 |
0.294 | 5.0 | 11360 | 0.6731 | 0.0186 | 0.8434 | 0.3657 | 0.8790 | 0.8763 | 0.7702 | 0.2942 | 0.8399 | 0.8618 | 0.9320 | 0.7288 | 0.9320 | 0.9432 | 0.9581 | 0.6841 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.13.3