metadata
license: mit
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: SETH_5e-05_0404_ES6_strict_tok
results: []
SETH_5e-05_0404_ES6_strict_tok
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: 0.0824
- Precision: 0.7891
- Recall: 0.7470
- F1: 0.7675
- Accuracy: 0.9741
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 |
|---|---|---|---|---|---|---|---|
| 0.4311 | 0.96 | 25 | 0.1785 | 0.7 | 0.0120 | 0.0237 | 0.9354 |
| 0.1235 | 1.92 | 50 | 0.0961 | 0.6732 | 0.7091 | 0.6907 | 0.9655 |
| 0.0749 | 2.88 | 75 | 0.0858 | 0.6801 | 0.8417 | 0.7523 | 0.9692 |
| 0.063 | 3.85 | 100 | 0.0857 | 0.6764 | 0.8744 | 0.7628 | 0.9666 |
| 0.0521 | 4.81 | 125 | 0.0757 | 0.7419 | 0.7522 | 0.7470 | 0.9723 |
| 0.0336 | 5.77 | 150 | 0.0829 | 0.7170 | 0.7935 | 0.7533 | 0.9714 |
| 0.0287 | 6.73 | 175 | 0.0824 | 0.7891 | 0.7470 | 0.7675 | 0.9741 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3