bert-unformatted-network-data-test

This model is a fine-tuned version of roberta-large on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0000

EXAMPLE FULL NAMES:

label_0 = malicious (UDP-lag DDoS), label_1 = benign

1. malicious from training dataset
2. benign from training dataset
3. malicious outside training dataset
4. malicious outside training dataset 2
5. benign outside training dataset
6. benign outside training dataset 2
7. benign then malicious same entry
8. malicious then benign same entry

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: 5

Training results

Training Loss	Epoch	Step	Validation Loss
0.0139	1.0	750	0.0000
0.0	2.0	1500	0.0000
0.0	3.0	2250	0.0000
0.0	4.0	3000	0.0000
0.0	5.0	3750	0.0000

Framework versions

• Transformers 4.42.0.dev0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1