bert-phishing-classifier_teacher

This model is a fine-tuned version of google-bert/bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2881
• Accuracy: 0.867
• Auc: 0.951

Model description

Teacher model for knowledge distillation example.

Video | Blog | Example code

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: 0.0002
• 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

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Auc
0.4916	1.0	263	0.4228	0.784	0.915
0.3894	2.0	526	0.3586	0.818	0.932
0.3837	3.0	789	0.3144	0.86	0.939
0.3574	4.0	1052	0.4494	0.807	0.942
0.3517	5.0	1315	0.3287	0.86	0.947
0.3518	6.0	1578	0.3042	0.871	0.949
0.3185	7.0	1841	0.2900	0.862	0.949
0.3267	8.0	2104	0.2958	0.876	0.95
0.3153	9.0	2367	0.2881	0.867	0.951
0.3061	10.0	2630	0.2963	0.873	0.951

Framework versions

• Transformers 4.44.2
• Pytorch 2.2.2
• Datasets 2.21.0
• Tokenizers 0.19.1