<!-- 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. -->
Variome_5e-05_30_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: 0.0631
- Precision: 0.5610
- Recall: 0.5068
- F1: 0.5325
- Accuracy: 0.9859
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 |
---|---|---|---|---|---|---|---|
0.6582 | 0.51 | 25 | 0.1765 | 0.0 | 0.0 | 0.0 | 0.9769 |
0.1545 | 1.02 | 50 | 0.1746 | 0.0 | 0.0 | 0.0 | 0.9769 |
0.1544 | 1.53 | 75 | 0.1770 | 0.0 | 0.0 | 0.0 | 0.9769 |
0.1608 | 2.04 | 100 | 0.1752 | 0.0 | 0.0 | 0.0 | 0.9769 |
0.1552 | 2.55 | 125 | 0.1726 | 0.0 | 0.0 | 0.0 | 0.9769 |
0.1591 | 3.06 | 150 | 0.1582 | 0.0 | 0.0 | 0.0 | 0.9769 |
0.1185 | 3.57 | 175 | 0.1142 | 0.2978 | 0.0703 | 0.1138 | 0.9778 |
0.0979 | 4.08 | 200 | 0.1046 | 0.2865 | 0.1584 | 0.2041 | 0.9792 |
0.0889 | 4.59 | 225 | 0.0923 | 0.3965 | 0.2151 | 0.2789 | 0.9811 |
0.0749 | 5.1 | 250 | 0.0819 | 0.4126 | 0.3295 | 0.3664 | 0.9827 |
0.0622 | 5.61 | 275 | 0.0756 | 0.4497 | 0.3987 | 0.4227 | 0.9838 |
0.0635 | 6.12 | 300 | 0.0699 | 0.4970 | 0.4355 | 0.4642 | 0.9850 |
0.048 | 6.63 | 325 | 0.0672 | 0.5225 | 0.4512 | 0.4842 | 0.9852 |
0.0486 | 7.14 | 350 | 0.0663 | 0.5457 | 0.4827 | 0.5122 | 0.9852 |
0.0464 | 7.65 | 375 | 0.0666 | 0.5623 | 0.4879 | 0.5225 | 0.9856 |
0.043 | 8.16 | 400 | 0.0636 | 0.5464 | 0.5005 | 0.5225 | 0.9857 |
0.0393 | 8.67 | 425 | 0.0636 | 0.5693 | 0.4869 | 0.5249 | 0.9860 |
0.036 | 9.18 | 450 | 0.0636 | 0.5641 | 0.4942 | 0.5268 | 0.9858 |
0.0373 | 9.69 | 475 | 0.0637 | 0.5735 | 0.5037 | 0.5363 | 0.9860 |
0.0382 | 10.2 | 500 | 0.0631 | 0.5610 | 0.5068 | 0.5325 | 0.9859 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2