<!-- 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_5e-05_0404_ES6_strict_2
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: 0.0578
- Precision: 0.7121
- Recall: 0.8812
- F1: 0.7877
- Accuracy: 0.9827
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: 2000
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.38 | 0.96 | 25 | 0.1107 | 0.4376 | 0.4768 | 0.4563 | 0.9653 |
0.0752 | 1.92 | 50 | 0.0615 | 0.6796 | 0.8468 | 0.7540 | 0.9797 |
0.0437 | 2.88 | 75 | 0.0502 | 0.7317 | 0.8589 | 0.7902 | 0.9820 |
0.0334 | 3.85 | 100 | 0.0523 | 0.7228 | 0.8933 | 0.7991 | 0.9820 |
0.0273 | 4.81 | 125 | 0.0486 | 0.7668 | 0.8657 | 0.8133 | 0.9838 |
0.0223 | 5.77 | 150 | 0.0474 | 0.7949 | 0.8606 | 0.8264 | 0.9855 |
0.0152 | 6.73 | 175 | 0.0524 | 0.8569 | 0.7831 | 0.8183 | 0.9855 |
0.0143 | 7.69 | 200 | 0.0578 | 0.7121 | 0.8812 | 0.7877 | 0.9827 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3