<!-- 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-Large-LitCovid-v1.3.1c
This model is a fine-tuned version of michiyasunaga/BioLinkBERT-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1423
- Hamming loss: 0.0115
- F1 micro: 0.8955
- F1 macro: 0.5189
- F1 weighted: 0.8999
- F1 samples: 0.9001
- Precision micro: 0.8699
- Precision macro: 0.4571
- Precision weighted: 0.8797
- Precision samples: 0.8987
- Recall micro: 0.9228
- Recall macro: 0.6461
- Recall weighted: 0.9228
- Recall samples: 0.9346
- Roc Auc: 0.9575
- Accuracy: 0.7369
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: 4
- eval_batch_size: 4
- 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 | 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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
2.3002 | 1.0 | 9086 | 0.8219 | 0.0155 | 0.8654 | 0.4167 | 0.8761 | 0.8797 | 0.8090 | 0.3554 | 0.8345 | 0.8627 | 0.9302 | 0.6257 | 0.9302 | 0.9414 | 0.9589 | 0.6796 |
1.273 | 2.0 | 18172 | 0.7056 | 0.0145 | 0.8730 | 0.4396 | 0.8878 | 0.8898 | 0.8208 | 0.3638 | 0.8526 | 0.8772 | 0.9323 | 0.6919 | 0.9323 | 0.9439 | 0.9604 | 0.7050 |
0.8734 | 3.0 | 27258 | 0.8218 | 0.0123 | 0.8896 | 0.4846 | 0.8969 | 0.8958 | 0.8557 | 0.4219 | 0.8729 | 0.8893 | 0.9264 | 0.6671 | 0.9264 | 0.9378 | 0.9588 | 0.7249 |
0.7889 | 4.0 | 36344 | 0.9218 | 0.0118 | 0.8931 | 0.5037 | 0.9001 | 0.8983 | 0.8651 | 0.4391 | 0.8810 | 0.8966 | 0.9230 | 0.6716 | 0.9230 | 0.9349 | 0.9574 | 0.7333 |
0.4284 | 5.0 | 45430 | 1.1423 | 0.0115 | 0.8955 | 0.5189 | 0.8999 | 0.9001 | 0.8699 | 0.4571 | 0.8797 | 0.8987 | 0.9228 | 0.6461 | 0.9228 | 0.9346 | 0.9575 | 0.7369 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3