synthetic_training_output_5k

This model is a fine-tuned version of cyberseclabs/bert-classify-url-v1 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0000
• Accuracy: 1.0
• Precision: 1.0
• Recall: 1.0
• F1: 1.0
• Roc Auc: 1.0

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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Roc Auc
0.0898	0.3906	250	0.0132	0.9971	0.8761	0.99	0.9296	0.9991
0.0431	0.7812	500	0.0033	0.9994	0.9802	0.99	0.9851	0.9999
0.0349	1.1719	750	0.0035	0.9992	0.9706	0.99	0.9802	0.9999
0.0137	1.5625	1000	0.0065	0.9986	0.9346	1.0	0.9662	1.0000
0.0207	1.9531	1250	0.0014	0.9996	0.9804	1.0	0.9901	1.0
0.0079	2.3438	1500	0.0005	0.9998	0.9901	1.0	0.9950	1.0
0.0041	2.7344	1750	0.0000	1.0	1.0	1.0	1.0	1.0

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1