metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: cybersecurity-ner
results: []
datasets:
- bnsapa/cybersecurity-ner
language:
- en
library_name: transformers
widget:
- text: microsoft and google are working to build AI models
- text: >-
Having obtained the necessary permissions from the user, Riltok contacts
its C&C server.
- text: Tweets in Twitter can be controversial
cybersecurity-ner
This model is a fine-tuned version of distilbert-base-uncased on the cybersecurity-ner dataset. It achieves the following results on the evaluation set:
- Loss: 0.2196
- Precision: 0.7942
- Recall: 0.7925
- F1: 0.7933
- Accuracy: 0.9508
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 167 | 0.2492 | 0.6870 | 0.7406 | 0.7128 | 0.9293 |
| No log | 2.0 | 334 | 0.2026 | 0.7733 | 0.7346 | 0.7534 | 0.9420 |
| 0.2118 | 3.0 | 501 | 0.1895 | 0.7735 | 0.7934 | 0.7833 | 0.9493 |
| 0.2118 | 4.0 | 668 | 0.1834 | 0.7785 | 0.8189 | 0.7982 | 0.9511 |
| 0.2118 | 5.0 | 835 | 0.2060 | 0.8113 | 0.7965 | 0.8039 | 0.9522 |
| 0.0507 | 6.0 | 1002 | 0.2153 | 0.7692 | 0.8226 | 0.7950 | 0.9511 |
| 0.0507 | 7.0 | 1169 | 0.2141 | 0.7866 | 0.7962 | 0.7914 | 0.9507 |
| 0.0507 | 8.0 | 1336 | 0.2196 | 0.7942 | 0.7925 | 0.7933 | 0.9508 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0