|
--- |
|
license: mit |
|
base_model: microsoft/deberta-v3-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
model-index: |
|
- name: deberta-pii-finetuned |
|
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. --> |
|
|
|
# deberta-pii-finetuned |
|
|
|
This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0065 |
|
- F Beta: 0.9611 |
|
- Precision: 0.9932 |
|
- Recall: 0.9598 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.05 |
|
- num_epochs: 3 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F Beta | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|:------:| |
|
| 0.0291 | 0.46 | 300 | 0.0104 | 0.9756 | 0.9854 | 0.9752 | |
|
| 0.0062 | 0.93 | 600 | 0.0041 | 0.9830 | 0.9901 | 0.9827 | |
|
| 0.0044 | 1.39 | 900 | 0.0057 | 0.9713 | 0.9895 | 0.9706 | |
|
| 0.0258 | 1.85 | 1200 | 0.0040 | 0.9799 | 0.9920 | 0.9794 | |
|
| 0.0135 | 2.32 | 1500 | 0.0050 | 0.9845 | 0.9943 | 0.9841 | |
|
| 0.0023 | 2.78 | 1800 | 0.0065 | 0.9611 | 0.9932 | 0.9598 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.2 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.15.0 |
|
|
