|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: Variome_5e-05_0404_ES6 |
|
results: [] |
|
--- |
|
|
|
<!-- 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_0404_ES6 |
|
|
|
This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0695 |
|
- Precision: 0.6584 |
|
- Recall: 0.6123 |
|
- F1: 0.6345 |
|
- Accuracy: 0.9866 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.56 | 0.13 | 25 | 0.1838 | 0.0 | 0.0 | 0.0 | 0.9759 | |
|
| 0.1843 | 0.26 | 50 | 0.1810 | 0.0 | 0.0 | 0.0 | 0.9759 | |
|
| 0.1822 | 0.39 | 75 | 0.1823 | 0.0 | 0.0 | 0.0 | 0.9759 | |
|
| 0.1797 | 0.52 | 100 | 0.1800 | 0.0 | 0.0 | 0.0 | 0.9759 | |
|
| 0.1618 | 0.65 | 125 | 0.1838 | 0.0 | 0.0 | 0.0 | 0.9759 | |
|
| 0.1735 | 0.79 | 150 | 0.1784 | 0.0 | 0.0 | 0.0 | 0.9759 | |
|
| 0.1654 | 0.92 | 175 | 0.1673 | 0.0 | 0.0 | 0.0 | 0.9759 | |
|
| 0.1171 | 1.05 | 200 | 0.1367 | 0.1538 | 0.0038 | 0.0075 | 0.9760 | |
|
| 0.1366 | 1.18 | 225 | 0.1333 | 0.1881 | 0.1881 | 0.1881 | 0.9752 | |
|
| 0.1262 | 1.31 | 250 | 0.1110 | 0.2137 | 0.1411 | 0.1699 | 0.9771 | |
|
| 0.1102 | 1.44 | 275 | 0.1016 | 0.3440 | 0.2582 | 0.2950 | 0.9789 | |
|
| 0.099 | 1.57 | 300 | 0.0918 | 0.4712 | 0.3695 | 0.4142 | 0.9813 | |
|
| 0.0843 | 1.7 | 325 | 0.0868 | 0.4654 | 0.3359 | 0.3902 | 0.9812 | |
|
| 0.0833 | 1.83 | 350 | 0.0830 | 0.5755 | 0.3512 | 0.4362 | 0.9818 | |
|
| 0.0689 | 1.96 | 375 | 0.0807 | 0.5766 | 0.3973 | 0.4705 | 0.9828 | |
|
| 0.0656 | 2.09 | 400 | 0.0781 | 0.5361 | 0.4923 | 0.5133 | 0.9839 | |
|
| 0.0625 | 2.23 | 425 | 0.0769 | 0.5802 | 0.4722 | 0.5206 | 0.9839 | |
|
| 0.0707 | 2.36 | 450 | 0.0748 | 0.5979 | 0.4453 | 0.5105 | 0.9837 | |
|
| 0.0568 | 2.49 | 475 | 0.0732 | 0.5515 | 0.5345 | 0.5429 | 0.9844 | |
|
| 0.0659 | 2.62 | 500 | 0.0703 | 0.6244 | 0.5154 | 0.5647 | 0.9845 | |
|
| 0.0601 | 2.75 | 525 | 0.0674 | 0.6174 | 0.5528 | 0.5833 | 0.9848 | |
|
| 0.0554 | 2.88 | 550 | 0.0667 | 0.6230 | 0.5614 | 0.5906 | 0.9855 | |
|
| 0.0634 | 3.01 | 575 | 0.0699 | 0.6605 | 0.5509 | 0.6007 | 0.9856 | |
|
| 0.0449 | 3.14 | 600 | 0.0694 | 0.6249 | 0.5691 | 0.5957 | 0.9850 | |
|
| 0.0435 | 3.27 | 625 | 0.0693 | 0.5868 | 0.5710 | 0.5788 | 0.9847 | |
|
| 0.0338 | 3.4 | 650 | 0.0710 | 0.6321 | 0.5672 | 0.5979 | 0.9858 | |
|
| 0.0405 | 3.53 | 675 | 0.0669 | 0.6245 | 0.5825 | 0.6028 | 0.9859 | |
|
| 0.0459 | 3.66 | 700 | 0.0665 | 0.6808 | 0.5710 | 0.6211 | 0.9862 | |
|
| 0.0471 | 3.8 | 725 | 0.0669 | 0.6162 | 0.5902 | 0.6029 | 0.9845 | |
|
| 0.0477 | 3.93 | 750 | 0.0657 | 0.6655 | 0.5595 | 0.6079 | 0.9859 | |
|
| 0.0476 | 4.06 | 775 | 0.0652 | 0.6483 | 0.6084 | 0.6277 | 0.9859 | |
|
| 0.0419 | 4.19 | 800 | 0.0679 | 0.6134 | 0.5969 | 0.6051 | 0.9854 | |
|
| 0.036 | 4.32 | 825 | 0.0693 | 0.6598 | 0.5864 | 0.6209 | 0.9854 | |
|
| 0.0372 | 4.45 | 850 | 0.0666 | 0.6474 | 0.6008 | 0.6232 | 0.9859 | |
|
| 0.0309 | 4.58 | 875 | 0.0702 | 0.6811 | 0.5883 | 0.6313 | 0.9864 | |
|
| 0.0301 | 4.71 | 900 | 0.0659 | 0.6804 | 0.5864 | 0.6299 | 0.9866 | |
|
| 0.0364 | 4.84 | 925 | 0.0651 | 0.6738 | 0.6008 | 0.6352 | 0.9867 | |
|
| 0.0321 | 4.97 | 950 | 0.0640 | 0.6638 | 0.5931 | 0.6265 | 0.9867 | |
|
| 0.0296 | 5.1 | 975 | 0.0657 | 0.6920 | 0.5845 | 0.6337 | 0.9868 | |
|
| 0.0278 | 5.24 | 1000 | 0.0668 | 0.6739 | 0.5988 | 0.6341 | 0.9866 | |
|
| 0.0273 | 5.37 | 1025 | 0.0673 | 0.6568 | 0.5969 | 0.6254 | 0.9867 | |
|
| 0.0254 | 5.5 | 1050 | 0.0677 | 0.6969 | 0.5893 | 0.6386 | 0.9871 | |
|
| 0.0271 | 5.63 | 1075 | 0.0658 | 0.6667 | 0.6104 | 0.6373 | 0.9861 | |
|
| 0.025 | 5.76 | 1100 | 0.0695 | 0.6584 | 0.6123 | 0.6345 | 0.9866 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.4 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.2 |
|
|
