Downloads · 30 days
7
18% of all-time downloads
SecBERT-DNRTI
Cyber-ThreaD/SecBERT-DNRTI
SecBERT-DNRTI is a token classification model from Cyber-ThreaD. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
39
Public
Parameters
82.9M
332 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors332 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Dec 6, 2023
- Updated
- Dec 6, 2023
- SHA
- 2f1c9d55
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- 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. -->
dnrti_secbert
This model is a fine-tuned version of jackaduma/SecBERT on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2274
- Precision: 0.7405
- Recall: 0.7780
- F1: 0.7588
- Accuracy: 0.9389
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.6137 | 0.76 | 500 | 0.3731 | 0.5348 | 0.5951 | 0.5633 | 0.8842 |
| 0.2993 | 1.52 | 1000 | 0.2853 | 0.6684 | 0.6665 | 0.6674 | 0.9131 |
| 0.2157 | 2.28 | 1500 | 0.2624 | 0.6685 | 0.7282 | 0.6971 | 0.9212 |
| 0.152 | 3.04 | 2000 | 0.2414 | 0.6923 | 0.7619 | 0.7254 | 0.9308 |
| 0.1047 | 3.81 | 2500 | 0.2274 | 0.7405 | 0.7780 | 0.7588 | 0.9389 |
| 0.0725 | 4.57 | 3000 | 0.2563 | 0.7262 | 0.7964 | 0.7597 | 0.9370 |
| 0.0589 | 5.33 | 3500 | 0.2615 | 0.7489 | 0.8024 | 0.7747 | 0.9411 |
| 0.0442 | 6.09 | 4000 | 0.2638 | 0.7543 | 0.8061 | 0.7793 | 0.9434 |
| 0.0344 | 6.85 | 4500 | 0.2671 | 0.7635 | 0.8088 | 0.7855 | 0.9448 |
| 0.0282 | 7.61 | 5000 | 0.2861 | 0.7584 | 0.8111 | 0.7839 | 0.9439 |
| 0.0226 | 8.37 | 5500 | 0.2849 | 0.7693 | 0.8093 | 0.7888 | 0.9456 |
| 0.0207 | 9.13 | 6000 | 0.2932 | 0.7643 | 0.8185 | 0.7905 | 0.9456 |
| 0.0181 | 9.89 | 6500 | 0.2952 | 0.7665 | 0.8167 | 0.7908 | 0.9459 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Dec 6, 2023
- Updated
- Dec 6, 2023