metadata
language:
- zh
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- gyr66/privacy_detection
metrics:
- precision
- recall
- f1
- accuracy
base_model: gyr66/RoBERTa-finetuned-privacy-detection
model-index:
- name: RoBERTa-finetuned-privacy-detection
results:
- task:
type: token-classification
name: Token Classification
dataset:
name: gyr66/privacy_detection
type: gyr66/privacy_detection
config: privacy_detection
split: train
args: privacy_detection
metrics:
- type: precision
value: 0.6168845082494108
name: Precision
- type: recall
value: 0.7248237663645518
name: Recall
- type: f1
value: 0.6665123278157193
name: F1
- type: accuracy
value: 0.9061190926862569
name: Accuracy
RoBERTa-finetuned-privacy-detection
This model is a fine-tuned version of gyr66/RoBERTa-finetuned-privacy-detection on the gyr66/privacy_detection dataset. It achieves the following results on the evaluation set:
- Loss: 0.3534
- Precision: 0.6169
- Recall: 0.7248
- F1: 0.6665
- Accuracy: 0.9061
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: 56
- eval_batch_size: 56
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2027 | 1.0 | 36 | 0.3485 | 0.5913 | 0.7273 | 0.6523 | 0.9030 |
| 0.1652 | 2.0 | 72 | 0.3534 | 0.6153 | 0.7314 | 0.6684 | 0.9053 |
| 0.143 | 3.0 | 108 | 0.3534 | 0.6169 | 0.7248 | 0.6665 | 0.9061 |
Framework versions
- Transformers 4.27.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.2