<!-- 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. -->
BioLinkBERT-LitCovid-v1.3.1
This model is a fine-tuned version of michiyasunaga/BioLinkBERT-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6883
- Hamming loss: 0.0171
- F1 micro: 0.8542
- F1 macro: 0.3828
- F1 weighted: 0.8818
- F1 samples: 0.8804
- Precision micro: 0.7855
- Precision macro: 0.3067
- Precision weighted: 0.8407
- Precision samples: 0.8641
- Recall micro: 0.9360
- Recall macro: 0.7145
- Recall weighted: 0.9360
- Recall samples: 0.9459
- Roc Auc: 0.9607
- Accuracy: 0.6896
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
1.0638 | 1.0 | 2272 | 0.4414 | 0.0398 | 0.7141 | 0.2594 | 0.8318 | 0.8178 | 0.5807 | 0.2077 | 0.7729 | 0.7843 | 0.9269 | 0.8062 | 0.9269 | 0.9422 | 0.9445 | 0.5545 |
0.8571 | 2.0 | 4544 | 0.4364 | 0.0230 | 0.8122 | 0.3367 | 0.8645 | 0.8517 | 0.7236 | 0.2666 | 0.8255 | 0.8284 | 0.9254 | 0.7835 | 0.9254 | 0.9396 | 0.9527 | 0.6211 |
0.6709 | 3.0 | 6816 | 0.4827 | 0.0218 | 0.8222 | 0.3405 | 0.8723 | 0.8638 | 0.7297 | 0.2708 | 0.8239 | 0.8381 | 0.9415 | 0.7770 | 0.9415 | 0.9513 | 0.9609 | 0.6488 |
0.5093 | 4.0 | 9088 | 0.5695 | 0.0184 | 0.8457 | 0.3795 | 0.8781 | 0.8753 | 0.7692 | 0.3006 | 0.8333 | 0.8556 | 0.9390 | 0.7605 | 0.9390 | 0.9482 | 0.9615 | 0.6760 |
0.2957 | 5.0 | 11360 | 0.6883 | 0.0171 | 0.8542 | 0.3828 | 0.8818 | 0.8804 | 0.7855 | 0.3067 | 0.8407 | 0.8641 | 0.9360 | 0.7145 | 0.9360 | 0.9459 | 0.9607 | 0.6896 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.13.3