<!-- 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_10e-5_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: 0.0704
- Precision: 0.7565
- Recall: 0.8021
- F1: 0.7786
- Accuracy: 0.9831
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: 0.0001
- 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 |
---|---|---|---|---|---|---|---|
0.2855 | 0.96 | 25 | 0.1080 | 0.7375 | 0.1015 | 0.1785 | 0.9600 |
0.0776 | 1.92 | 50 | 0.0720 | 0.5057 | 0.7659 | 0.6092 | 0.9740 |
0.0497 | 2.88 | 75 | 0.0557 | 0.6626 | 0.8382 | 0.7401 | 0.9792 |
0.0377 | 3.85 | 100 | 0.0620 | 0.6751 | 0.8296 | 0.7444 | 0.9800 |
0.0346 | 4.81 | 125 | 0.0652 | 0.6652 | 0.8072 | 0.7294 | 0.9773 |
0.0273 | 5.77 | 150 | 0.0643 | 0.6729 | 0.8640 | 0.7566 | 0.9801 |
0.0208 | 6.73 | 175 | 0.0720 | 0.6709 | 0.8244 | 0.7398 | 0.9795 |
0.0156 | 7.69 | 200 | 0.0623 | 0.6996 | 0.8176 | 0.7540 | 0.9813 |
0.0115 | 8.65 | 225 | 0.0733 | 0.6721 | 0.8571 | 0.7534 | 0.9788 |
0.0088 | 9.62 | 250 | 0.0704 | 0.7565 | 0.8021 | 0.7786 | 0.9831 |
Framework versions
- Transformers 4.27.3
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2