<!-- 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. -->
New_BioRED_model_1
This model is a fine-tuned version of microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4105
- Precision: 0.4596
- Recall: 0.2902
- F1: 0.3558
- Accuracy: 0.8605
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: 1e-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: 15
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 13 | 0.7199 | 0.0 | 0.0 | 0.0 | 0.8273 |
No log | 2.0 | 26 | 0.6140 | 0.1663 | 0.0112 | 0.0210 | 0.8316 |
No log | 3.0 | 39 | 0.5403 | 0.3494 | 0.1336 | 0.1933 | 0.8462 |
No log | 4.0 | 52 | 0.4823 | 0.3732 | 0.1895 | 0.2514 | 0.8501 |
No log | 5.0 | 65 | 0.4644 | 0.3951 | 0.2304 | 0.2911 | 0.8534 |
No log | 6.0 | 78 | 0.4450 | 0.4086 | 0.2515 | 0.3114 | 0.8553 |
No log | 7.0 | 91 | 0.4324 | 0.4293 | 0.2667 | 0.3290 | 0.8570 |
No log | 8.0 | 104 | 0.4242 | 0.4413 | 0.2684 | 0.3338 | 0.8583 |
No log | 9.0 | 117 | 0.4209 | 0.4452 | 0.2773 | 0.3417 | 0.8587 |
No log | 10.0 | 130 | 0.4170 | 0.4499 | 0.2854 | 0.3493 | 0.8593 |
No log | 11.0 | 143 | 0.4131 | 0.4568 | 0.2891 | 0.3541 | 0.8600 |
No log | 12.0 | 156 | 0.4140 | 0.4478 | 0.2962 | 0.3566 | 0.8588 |
No log | 13.0 | 169 | 0.4120 | 0.4660 | 0.2889 | 0.3567 | 0.8608 |
No log | 14.0 | 182 | 0.4116 | 0.4560 | 0.2911 | 0.3554 | 0.8600 |
No log | 15.0 | 195 | 0.4105 | 0.4596 | 0.2902 | 0.3558 | 0.8605 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.12.1
- Datasets 2.6.1
- Tokenizers 0.11.0