| | --- |
| | license: apache-2.0 |
| | tags: |
| | - generated_from_trainer |
| | metrics: |
| | - accuracy |
| | model-index: |
| | - name: BioLinkBERT-LitCovid-1.4 |
| | results: [] |
| | --- |
| | |
| | <!-- 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-1.4 |
| |
|
| | This model is a fine-tuned version of [michiyasunaga/BioLinkBERT-base](https://huggingface.co/michiyasunaga/BioLinkBERT-base) on an unknown dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 0.5613 |
| | - Hamming loss: 0.0775 |
| | - F1 micro: 0.6253 |
| | - F1 macro: 0.4797 |
| | - F1 weighted: 0.7043 |
| | - F1 samples: 0.6321 |
| | - Precision micro: 0.4806 |
| | - Precision macro: 0.3631 |
| | - Precision weighted: 0.6169 |
| | - Precision samples: 0.5276 |
| | - Recall micro: 0.8947 |
| | - Recall macro: 0.8442 |
| | - Recall weighted: 0.8947 |
| | - Recall samples: 0.9099 |
| | - Roc Auc: 0.9097 |
| | - Accuracy: 0.0849 |
| |
|
| | ## 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 |
| | - gradient_accumulation_steps: 2 |
| | - total_train_batch_size: 32 |
| | - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| | - lr_scheduler_type: linear |
| | - num_epochs: 5 |
| | - mixed_precision_training: Native AMP |
| | |
| | ### 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 | |
| | |:-------------:|:-----:|:----:|:---------------:|:------------:|:--------:|:--------:|:-----------:|:----------:|:---------------:|:---------------:|:------------------:|:-----------------:|:------------:|:------------:|:---------------:|:--------------:|:-------:|:--------:| |
| | | 0.6654 | 1.0 | 1151 | 0.6313 | 0.1143 | 0.5259 | 0.3963 | 0.6460 | 0.5359 | 0.3756 | 0.2909 | 0.5586 | 0.4182 | 0.8764 | 0.8497 | 0.8764 | 0.8940 | 0.8814 | 0.0227 | |
| | | 0.5313 | 2.0 | 2303 | 0.5682 | 0.0997 | 0.5655 | 0.4266 | 0.6717 | 0.5784 | 0.4128 | 0.3161 | 0.5789 | 0.4624 | 0.8972 | 0.8620 | 0.8972 | 0.9120 | 0.8988 | 0.0492 | |
| | | 0.4594 | 3.0 | 3454 | 0.5529 | 0.0884 | 0.5938 | 0.4517 | 0.6907 | 0.6012 | 0.4446 | 0.3394 | 0.6041 | 0.4883 | 0.8939 | 0.8549 | 0.8939 | 0.9094 | 0.9034 | 0.0586 | |
| | | 0.3966 | 4.0 | 4606 | 0.5580 | 0.0797 | 0.6193 | 0.4739 | 0.7014 | 0.6245 | 0.4731 | 0.3579 | 0.6129 | 0.5166 | 0.8965 | 0.8476 | 0.8965 | 0.9109 | 0.9093 | 0.0751 | |
| | | 0.3693 | 5.0 | 5755 | 0.5613 | 0.0775 | 0.6253 | 0.4797 | 0.7043 | 0.6321 | 0.4806 | 0.3631 | 0.6169 | 0.5276 | 0.8947 | 0.8442 | 0.8947 | 0.9099 | 0.9097 | 0.0849 | |
| | |
| | |
| | ### Framework versions |
| | |
| | - Transformers 4.28.0 |
| | - Pytorch 2.3.0+cu121 |
| | - Datasets 2.20.0 |
| | - Tokenizers 0.13.3 |
| | |
