|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
base_model: google-bert/bert-base-uncased |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: bert-wellness-classifier |
|
|
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. --> |
|
|
|
|
|
# bert-wellness-classifier |
|
|
|
|
|
This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 1.0333 |
|
|
- Accuracy: 0.648 |
|
|
- Auc: 0.878 |
|
|
- Precision Class 0: 0.409 |
|
|
- Precision Class 1: 0.769 |
|
|
- Precision Class 2: 0.382 |
|
|
- Precision Class 3: 0.729 |
|
|
- Precision Class 4: 0.833 |
|
|
- Precision Class 5: 0.478 |
|
|
- Recall Class 0: 0.474 |
|
|
- Recall Class 1: 0.87 |
|
|
- Recall Class 2: 0.481 |
|
|
- Recall Class 3: 0.745 |
|
|
- Recall Class 4: 0.781 |
|
|
- Recall Class 5: 0.333 |
|
|
|
|
|
## 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: 0.001 |
|
|
- 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 |
|
|
- num_epochs: 10 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Auc | Precision Class 0 | Precision Class 1 | Precision Class 2 | Precision Class 3 | Precision Class 4 | Precision Class 5 | Recall Class 0 | Recall Class 1 | Recall Class 2 | Recall Class 3 | Recall Class 4 | Recall Class 5 | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----:|:-----------------:|:-----------------:|:-----------------:|:-----------------:|:-----------------:|:-----------------:|:--------------:|:--------------:|:--------------:|:--------------:|:--------------:|:--------------:| |
|
|
| 1.5028 | 1.0 | 62 | 1.1703 | 0.528 | 0.852 | 0.5 | 0.889 | 0.0 | 0.769 | 0.595 | 0.282 | 0.28 | 0.4 | 0.0 | 0.714 | 0.701 | 0.556 | |
|
|
| 1.1661 | 2.0 | 124 | 1.0814 | 0.575 | 0.868 | 0.6 | 0.515 | 0.375 | 0.935 | 0.712 | 0.333 | 0.36 | 0.85 | 0.136 | 0.69 | 0.627 | 0.611 | |
|
|
| 1.0576 | 3.0 | 186 | 1.0438 | 0.585 | 0.876 | 0.394 | 0.737 | 0.308 | 0.755 | 0.719 | 0.467 | 0.52 | 0.7 | 0.545 | 0.881 | 0.612 | 0.194 | |
|
|
| 0.9603 | 4.0 | 248 | 1.0368 | 0.637 | 0.877 | 0.688 | 0.846 | 0.44 | 0.868 | 0.6 | 0.4 | 0.44 | 0.55 | 0.5 | 0.786 | 0.94 | 0.167 | |
|
|
| 0.8873 | 5.0 | 310 | 1.0208 | 0.571 | 0.877 | 0.667 | 0.75 | 0.333 | 0.886 | 0.651 | 0.311 | 0.48 | 0.6 | 0.091 | 0.738 | 0.612 | 0.639 | |
|
|
| 0.866 | 6.0 | 372 | 0.9809 | 0.604 | 0.877 | 0.484 | 0.684 | 0.312 | 0.892 | 0.671 | 0.259 | 0.6 | 0.65 | 0.227 | 0.786 | 0.821 | 0.194 | |
|
|
| 0.8203 | 7.0 | 434 | 0.9894 | 0.637 | 0.882 | 0.519 | 0.75 | 0.4 | 0.8 | 0.696 | 0.4 | 0.56 | 0.6 | 0.455 | 0.857 | 0.821 | 0.222 | |
|
|
| 0.8024 | 8.0 | 496 | 0.9797 | 0.632 | 0.882 | 0.484 | 0.682 | 0.45 | 0.889 | 0.693 | 0.393 | 0.6 | 0.75 | 0.409 | 0.762 | 0.776 | 0.306 | |
|
|
| 0.7558 | 9.0 | 558 | 0.9738 | 0.594 | 0.883 | 0.6 | 0.765 | 0.375 | 0.766 | 0.694 | 0.32 | 0.48 | 0.65 | 0.273 | 0.857 | 0.642 | 0.444 | |
|
|
| 0.7319 | 10.0 | 620 | 0.9632 | 0.632 | 0.884 | 0.519 | 0.722 | 0.36 | 0.8 | 0.708 | 0.44 | 0.56 | 0.65 | 0.409 | 0.857 | 0.761 | 0.306 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.45.1 |
|
|
- Pytorch 2.4.0 |
|
|
- Datasets 3.0.1 |
|
|
- Tokenizers 0.20.0 |
|
|
|
