<!-- 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-v1.2.4
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: 0.2160
- F1 micro: 0.8926
- F1 macro: 0.3237
- F1 weighted: 0.9016
- F1 samples: 0.9024
- Precision micro: 0.8426
- Precision macro: 0.2736
- Precision weighted: 0.8627
- Precision samples: 0.8871
- Recall micro: 0.9490
- Recall macro: 0.4834
- Recall weighted: 0.9490
- Recall samples: 0.9544
- Roc Auc: 0.9697
- Accuracy: 0.7353
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: 3
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0.4454 | 1.0 | 2248 | 0.3019 | 0.8637 | 0.2988 | 0.8757 | 0.8789 | 0.7937 | 0.2500 | 0.8205 | 0.8518 | 0.9471 | 0.4390 | 0.9471 | 0.9528 | 0.9669 | 0.6618 |
0.2453 | 2.0 | 4496 | 0.2696 | 0.8852 | 0.3387 | 0.8917 | 0.8947 | 0.8231 | 0.2862 | 0.8377 | 0.8701 | 0.9574 | 0.4723 | 0.9574 | 0.9602 | 0.9731 | 0.7056 |
0.1271 | 3.0 | 6744 | 0.2160 | 0.8926 | 0.3237 | 0.9016 | 0.9024 | 0.8426 | 0.2736 | 0.8627 | 0.8871 | 0.9490 | 0.4834 | 0.9490 | 0.9544 | 0.9697 | 0.7353 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3