<!-- 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-v1.2.3
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: 0.9317
- F1 micro: 0.7843
- F1 macro: 0.2816
- F1 weighted: 0.8523
- F1 samples: 0.8647
- Precision micro: 0.6737
- Precision macro: 0.2255
- Precision weighted: 0.7914
- Precision samples: 0.8417
- Recall micro: 0.9384
- Recall macro: 0.7715
- Recall weighted: 0.9384
- Recall samples: 0.9468
- Roc Auc: 0.9568
- Accuracy: 0.6515
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: 32
- eval_batch_size: 32
- 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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0.8024 | 1.0 | 1136 | 0.6487 | 0.6577 | 0.2288 | 0.7528 | 0.7600 | 0.5118 | 0.1747 | 0.6503 | 0.7007 | 0.9198 | 0.8185 | 0.9198 | 0.9253 | 0.9361 | 0.3919 |
0.639 | 2.0 | 2272 | 0.8280 | 0.7187 | 0.2482 | 0.8039 | 0.8088 | 0.5833 | 0.1935 | 0.7200 | 0.7602 | 0.9361 | 0.7535 | 0.9361 | 0.9441 | 0.9499 | 0.4986 |
0.5167 | 3.0 | 3408 | 0.8318 | 0.7589 | 0.2686 | 0.8342 | 0.8469 | 0.6372 | 0.2127 | 0.7628 | 0.8153 | 0.9382 | 0.7903 | 0.9382 | 0.9462 | 0.9546 | 0.6008 |
0.3641 | 4.0 | 4544 | 0.9231 | 0.7793 | 0.2788 | 0.8472 | 0.8578 | 0.6644 | 0.2220 | 0.7815 | 0.8290 | 0.9422 | 0.7678 | 0.9422 | 0.9497 | 0.9582 | 0.6311 |
0.3754 | 5.0 | 5680 | 0.9317 | 0.7843 | 0.2816 | 0.8523 | 0.8647 | 0.6737 | 0.2255 | 0.7914 | 0.8417 | 0.9384 | 0.7715 | 0.9384 | 0.9468 | 0.9568 | 0.6515 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3