VLAI for Severity
Collection
A collection of papers, models, and datasets supporting the AI and NLP components of the Vulnerability-Lookup project.
•
7 items
•
Updated
•
1
vulnerability-severity-classification-chinese-macbert-base
This model is a fine-tuned version of hfl/chinese-macbert-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6118
- Accuracy: 0.7832
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5706 | 1.0 | 3511 | 0.5875 | 0.7503 |
| 0.5364 | 2.0 | 7022 | 0.5596 | 0.7702 |
| 0.5483 | 3.0 | 10533 | 0.5518 | 0.7768 |
| 0.4161 | 4.0 | 14044 | 0.5757 | 0.7838 |
| 0.351 | 5.0 | 17555 | 0.6118 | 0.7832 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.9.1+cu128
- Datasets 4.4.1
- Tokenizers 0.22.1
- Downloads last month
- 166
Model tree for CIRCL/vulnerability-severity-classification-chinese-macbert-base
Base model
hfl/chinese-macbert-base