|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: BioBERT-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. --> |
|
|
|
# BioBERT-LitCovid-1.4 |
|
|
|
This model is a fine-tuned version of [dmis-lab/biobert-v1.1](https://huggingface.co/dmis-lab/biobert-v1.1) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5756 |
|
- Hamming loss: 0.0802 |
|
- F1 micro: 0.6160 |
|
- F1 macro: 0.4740 |
|
- F1 weighted: 0.6962 |
|
- F1 samples: 0.6217 |
|
- Precision micro: 0.4710 |
|
- Precision macro: 0.3578 |
|
- Precision weighted: 0.6089 |
|
- Precision samples: 0.5156 |
|
- Recall micro: 0.8901 |
|
- Recall macro: 0.8404 |
|
- Recall weighted: 0.8901 |
|
- Recall samples: 0.9055 |
|
- Roc Auc: 0.9061 |
|
- Accuracy: 0.0775 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------------:|:--------:|:--------:|:-----------:|:----------:|:---------------:|:---------------:|:------------------:|:-----------------:|:------------:|:------------:|:---------------:|:--------------:|:-------:|:--------:| |
|
| 0.6673 | 1.0 | 1151 | 0.6365 | 0.1262 | 0.5023 | 0.3822 | 0.6341 | 0.5084 | 0.3513 | 0.2799 | 0.5428 | 0.3829 | 0.8808 | 0.8538 | 0.8808 | 0.8981 | 0.8770 | 0.0088 | |
|
| 0.5371 | 2.0 | 2303 | 0.5721 | 0.1080 | 0.5442 | 0.4060 | 0.6607 | 0.5578 | 0.3916 | 0.2993 | 0.5701 | 0.4391 | 0.8917 | 0.8644 | 0.8917 | 0.9074 | 0.8919 | 0.0365 | |
|
| 0.4628 | 3.0 | 3454 | 0.5620 | 0.0940 | 0.5780 | 0.4370 | 0.6776 | 0.5874 | 0.4280 | 0.3248 | 0.5909 | 0.4739 | 0.8899 | 0.8572 | 0.8899 | 0.9054 | 0.8986 | 0.0510 | |
|
| 0.3925 | 4.0 | 4606 | 0.5744 | 0.0796 | 0.6160 | 0.4742 | 0.6960 | 0.6208 | 0.4728 | 0.3591 | 0.6113 | 0.5160 | 0.8837 | 0.8377 | 0.8837 | 0.9004 | 0.9035 | 0.0752 | |
|
| 0.3647 | 5.0 | 5755 | 0.5756 | 0.0802 | 0.6160 | 0.4740 | 0.6962 | 0.6217 | 0.4710 | 0.3578 | 0.6089 | 0.5156 | 0.8901 | 0.8404 | 0.8901 | 0.9055 | 0.9061 | 0.0775 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.0 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.13.3 |
|
|
