Bioformer-LitCovid-v1.4h
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: 0.5733
- Hamming loss: 0.0842
- F1 micro: 0.6047
- F1 macro: 0.4622
- F1 weighted: 0.6887
- F1 samples: 0.6127
- Precision micro: 0.4576
- Precision macro: 0.3466
- Precision weighted: 0.5990
- Precision samples: 0.5038
- Recall micro: 0.8912
- Recall macro: 0.8446
- Recall weighted: 0.8912
- Recall samples: 0.9055
- Roc Auc: 0.9044
- Accuracy: 0.0708
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: 5.451682398151845e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.08129918921555689
- num_epochs: 5
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.9164 | 1.0 | 576 | 0.6810 | 0.1510 | 0.4505 | 0.3468 | 0.6199 | 0.4653 | 0.3057 | 0.2568 | 0.5483 | 0.3450 | 0.8564 | 0.8656 | 0.8564 | 0.8750 | 0.8524 | 0.0078 |
| 0.6032 | 2.0 | 1152 | 0.5983 | 0.1154 | 0.5273 | 0.4002 | 0.6493 | 0.5373 | 0.3746 | 0.2939 | 0.5587 | 0.4139 | 0.8902 | 0.8651 | 0.8902 | 0.9050 | 0.8872 | 0.0263 |
| 0.4965 | 3.0 | 1728 | 0.5752 | 0.0975 | 0.5704 | 0.4372 | 0.6709 | 0.5795 | 0.4185 | 0.3237 | 0.5797 | 0.4617 | 0.8952 | 0.8536 | 0.8952 | 0.9089 | 0.8991 | 0.0479 |
| 0.4354 | 4.0 | 2304 | 0.5655 | 0.0863 | 0.5978 | 0.4554 | 0.6872 | 0.6050 | 0.4508 | 0.3406 | 0.6021 | 0.4948 | 0.8870 | 0.8503 | 0.8870 | 0.9024 | 0.9014 | 0.0636 |
| 0.3874 | 5.0 | 2880 | 0.5733 | 0.0842 | 0.6047 | 0.4622 | 0.6887 | 0.6127 | 0.4576 | 0.3466 | 0.5990 | 0.5038 | 0.8912 | 0.8446 | 0.8912 | 0.9055 | 0.9044 | 0.0708 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
- Downloads last month
- 9
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.