<!-- 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-v1.2.1
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: 0.2205
- F1 micro: 0.9016
- F1 macro: 0.8505
- F1 weighted: 0.9044
- F1 samples: 0.9056
- Precision micro: 0.8545
- Precision macro: 0.7857
- Precision weighted: 0.8625
- Precision samples: 0.8862
- Recall micro: 0.9540
- Recall macro: 0.9431
- Recall weighted: 0.9540
- Recall samples: 0.9610
- Roc Auc: 0.9578
- Accuracy: 0.7211
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: 4
Training results
Training Loss | Epoch | Step | Validation 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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0.2839 | 1.0 | 2211 | 0.2205 | 0.9016 | 0.8505 | 0.9044 | 0.9056 | 0.8545 | 0.7857 | 0.8625 | 0.8862 | 0.9540 | 0.9431 | 0.9540 | 0.9610 | 0.9578 | 0.7211 |
0.1926 | 2.0 | 4422 | 0.2477 | 0.9134 | 0.8734 | 0.9147 | 0.9159 | 0.8770 | 0.8309 | 0.8808 | 0.9026 | 0.9529 | 0.9283 | 0.9529 | 0.9590 | 0.9607 | 0.7554 |
0.1341 | 3.0 | 6633 | 0.2667 | 0.9155 | 0.8749 | 0.9164 | 0.9170 | 0.8823 | 0.8328 | 0.8851 | 0.9059 | 0.9513 | 0.9251 | 0.9513 | 0.9569 | 0.9606 | 0.7642 |
0.1161 | 4.0 | 8844 | 0.2864 | 0.9188 | 0.8783 | 0.9195 | 0.9202 | 0.8938 | 0.8451 | 0.8958 | 0.9150 | 0.9452 | 0.9173 | 0.9452 | 0.9525 | 0.9593 | 0.7758 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3