<!-- 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. -->
Bioformer-LitCovid-v1.2.2
This model is a fine-tuned version of bioformers/bioformer-litcovid on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2230
- F1 micro: 0.9107
- F1 macro: 0.8633
- F1 weighted: 0.9127
- F1 samples: 0.9132
- Precision micro: 0.8780
- Precision macro: 0.8105
- Precision weighted: 0.8840
- Precision samples: 0.9034
- Recall micro: 0.9460
- Recall macro: 0.9339
- Recall weighted: 0.9460
- Recall samples: 0.9534
- Roc Auc: 0.9577
- Accuracy: 0.7542
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 | 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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0.2625 | 1.0 | 2183 | 0.2415 | 0.8961 | 0.8499 | 0.8980 | 0.8996 | 0.8443 | 0.7844 | 0.8501 | 0.8775 | 0.9545 | 0.9373 | 0.9545 | 0.9590 | 0.9568 | 0.7083 |
0.2099 | 2.0 | 4366 | 0.2230 | 0.9107 | 0.8633 | 0.9127 | 0.9132 | 0.8780 | 0.8105 | 0.8840 | 0.9034 | 0.9460 | 0.9339 | 0.9460 | 0.9534 | 0.9577 | 0.7542 |
0.1735 | 3.0 | 6549 | 0.2661 | 0.9141 | 0.8732 | 0.9153 | 0.9155 | 0.8821 | 0.8361 | 0.8857 | 0.9057 | 0.9486 | 0.9203 | 0.9486 | 0.9543 | 0.9596 | 0.7653 |
0.1336 | 4.0 | 8732 | 0.2682 | 0.9187 | 0.8769 | 0.9197 | 0.9207 | 0.8953 | 0.8408 | 0.8979 | 0.9169 | 0.9435 | 0.9199 | 0.9435 | 0.9511 | 0.9589 | 0.7804 |
0.1102 | 5.0 | 10915 | 0.2825 | 0.9183 | 0.8778 | 0.9191 | 0.9199 | 0.8913 | 0.8413 | 0.8936 | 0.9134 | 0.9470 | 0.9202 | 0.9470 | 0.9536 | 0.9601 | 0.7792 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3