<!-- 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-LitCovid-v1.2.3
This model is a fine-tuned version of michiyasunaga/BioLinkBERT-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9691
- F1 micro: 0.8266
- F1 macro: 0.3107
- F1 weighted: 0.8821
- F1 samples: 0.8868
- Precision micro: 0.7335
- Precision macro: 0.2518
- Precision weighted: 0.8347
- Precision samples: 0.8699
- Recall micro: 0.9468
- Recall macro: 0.7764
- Recall weighted: 0.9468
- Recall samples: 0.9538
- Roc Auc: 0.9640
- Accuracy: 0.7104
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
1.1059 | 1.0 | 2272 | 0.7606 | 0.7517 | 0.2617 | 0.8428 | 0.8566 | 0.6257 | 0.2096 | 0.7778 | 0.8302 | 0.9412 | 0.7947 | 0.9412 | 0.9501 | 0.9553 | 0.6325 |
0.6408 | 2.0 | 4544 | 0.8639 | 0.8057 | 0.2965 | 0.8751 | 0.8786 | 0.7057 | 0.2399 | 0.8315 | 0.8626 | 0.9389 | 0.8070 | 0.9389 | 0.9484 | 0.9588 | 0.6961 |
0.6275 | 3.0 | 6816 | 0.9691 | 0.8266 | 0.3107 | 0.8821 | 0.8868 | 0.7335 | 0.2518 | 0.8347 | 0.8699 | 0.9468 | 0.7764 | 0.9468 | 0.9538 | 0.9640 | 0.7104 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3