metadata
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
model-index:
- name: deberta-pii-finetuned
results: []
deberta-pii-finetuned
This model is a fine-tuned version of microsoft/deberta-v3-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0018
- F Beta: 0.8127
- Precision: 0.9818
- Recall: 0.8071
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 |
|---|---|---|---|---|---|---|
| 0.0074 | 0.41 | 250 | 0.0022 | 0.9594 | 0.9851 | 0.9584 |
| 0.0031 | 0.82 | 500 | 0.0011 | 0.9541 | 0.9879 | 0.9528 |
| 0.0035 | 1.24 | 750 | 0.0015 | 0.8814 | 0.9869 | 0.8776 |
| 0.0029 | 1.65 | 1000 | 0.0024 | 0.7401 | 0.9849 | 0.7328 |
| 0.0016 | 2.06 | 1250 | 0.0015 | 0.8240 | 0.9810 | 0.8188 |
| 0.0012 | 2.47 | 1500 | 0.0020 | 0.7848 | 0.9812 | 0.7786 |
| 0.003 | 2.88 | 1750 | 0.0018 | 0.8127 | 0.9818 | 0.8071 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.15.0