<!-- 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. -->
SETH_29_03
This model is a fine-tuned version of microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0866
- Precision: 0.7204
- Recall: 0.8468
- F1: 0.7785
- Accuracy: 0.9819
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: 5e-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
- training_steps: 500
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.3731 | 0.96 | 25 | 0.1863 | 0.0 | 0.0 | 0.0 | 0.9583 |
0.1139 | 1.92 | 50 | 0.0862 | 0.4524 | 0.6540 | 0.5348 | 0.9664 |
0.0654 | 2.88 | 75 | 0.0737 | 0.5914 | 0.8244 | 0.6887 | 0.9739 |
0.051 | 3.85 | 100 | 0.0646 | 0.6340 | 0.8227 | 0.7161 | 0.9789 |
0.0444 | 4.81 | 125 | 0.0769 | 0.5938 | 0.8554 | 0.7010 | 0.9732 |
0.031 | 5.77 | 150 | 0.0660 | 0.6541 | 0.8692 | 0.7465 | 0.9784 |
0.026 | 6.73 | 175 | 0.0641 | 0.7186 | 0.8262 | 0.7686 | 0.9814 |
0.0217 | 7.69 | 200 | 0.0682 | 0.6985 | 0.8571 | 0.7697 | 0.9813 |
0.0167 | 8.65 | 225 | 0.0678 | 0.7246 | 0.7969 | 0.7590 | 0.9809 |
0.0129 | 9.62 | 250 | 0.0727 | 0.7488 | 0.7900 | 0.7688 | 0.9825 |
0.0107 | 10.58 | 275 | 0.0778 | 0.7242 | 0.8451 | 0.7800 | 0.9818 |
0.0085 | 11.54 | 300 | 0.0784 | 0.7188 | 0.8537 | 0.7805 | 0.9820 |
0.0064 | 12.5 | 325 | 0.0866 | 0.7204 | 0.8468 | 0.7785 | 0.9819 |
Framework versions
- Transformers 4.27.3
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2