| | --- |
| | license: mit |
| | tags: |
| | - generated_from_trainer |
| | metrics: |
| | - accuracy |
| | model-index: |
| | - name: PubMedELECTRA-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. --> |
| |
|
| | # PubMedELECTRA-LitCovid-1.4 |
| |
|
| | This model is a fine-tuned version of [microsoft/BiomedNLP-BiomedELECTRA-base-uncased-abstract](https://huggingface.co/microsoft/BiomedNLP-BiomedELECTRA-base-uncased-abstract) on an unknown dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 0.5898 |
| | - Hamming loss: 0.0967 |
| | - F1 micro: 0.5691 |
| | - F1 macro: 0.4329 |
| | - F1 weighted: 0.6693 |
| | - F1 samples: 0.5791 |
| | - Precision micro: 0.4198 |
| | - Precision macro: 0.3211 |
| | - Precision weighted: 0.5820 |
| | - Precision samples: 0.4666 |
| | - Recall micro: 0.8834 |
| | - Recall macro: 0.8456 |
| | - Recall weighted: 0.8834 |
| | - Recall samples: 0.8983 |
| | - Roc Auc: 0.8941 |
| | - Accuracy: 0.0504 |
| |
|
| | ## 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 | |
| | |:-------------:|:-----:|:----:|:---------------:|:------------:|:--------:|:--------:|:-----------:|:----------:|:---------------:|:---------------:|:------------------:|:-----------------:|:------------:|:------------:|:---------------:|:--------------:|:-------:|:--------:| |
| | | 0.7482 | 1.0 | 1151 | 0.7061 | 0.1518 | 0.4528 | 0.3484 | 0.6073 | 0.4584 | 0.3063 | 0.2528 | 0.5187 | 0.3313 | 0.8684 | 0.8422 | 0.8684 | 0.8869 | 0.8575 | 0.0023 | |
| | | 0.5987 | 2.0 | 2303 | 0.6241 | 0.1287 | 0.4983 | 0.3783 | 0.6327 | 0.5120 | 0.3469 | 0.2766 | 0.5412 | 0.3888 | 0.8840 | 0.8571 | 0.8840 | 0.8996 | 0.8771 | 0.0193 | |
| | | 0.5194 | 3.0 | 3454 | 0.5960 | 0.1079 | 0.5399 | 0.4108 | 0.6584 | 0.5500 | 0.3903 | 0.3056 | 0.5764 | 0.4339 | 0.8752 | 0.8513 | 0.8752 | 0.8921 | 0.8843 | 0.0351 | |
| | | 0.4471 | 4.0 | 4606 | 0.5900 | 0.0982 | 0.5653 | 0.4286 | 0.6681 | 0.5747 | 0.4157 | 0.3179 | 0.5810 | 0.4609 | 0.8830 | 0.8468 | 0.8830 | 0.8983 | 0.8931 | 0.0460 | |
| | | 0.422 | 5.0 | 5755 | 0.5898 | 0.0967 | 0.5691 | 0.4329 | 0.6693 | 0.5791 | 0.4198 | 0.3211 | 0.5820 | 0.4666 | 0.8834 | 0.8456 | 0.8834 | 0.8983 | 0.8941 | 0.0504 | |
| | |
| | |
| | ### Framework versions |
| | |
| | - Transformers 4.28.0 |
| | - Pytorch 2.3.0+cu121 |
| | - Datasets 2.20.0 |
| | - Tokenizers 0.13.3 |
| | |
