Modelpublic

AustinCarthy/Base_100Kphish_benignFall_IL_10K_OnlyPhish_from_benign_top_p_0.75_lr1e-6

sourceHugging Faceupdated 3y agoView on Hugging Face

0likes4downloads

Model Card

Base100KphishbenignFallIL10KOnlyPhishfrombenigntopp0.75_lr1e-6

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

—Loss: 0.0201
—Accuracy: 0.9978
—F1: 0.9766
—Precision: 0.9985
—Recall: 0.9556
—Roc Auc Score: 0.9778
—Tpr At Fpr 0.01: 0.9614

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: 1e-05
—trainbatchsize: 32
—evalbatchsize: 32
—seed: 42
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—num_epochs: 5.0
—mixedprecisiontraining: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Roc Auc Score	Tpr At Fpr 0.01
0.004	1.0	6563	0.0144	0.9980	0.9781	0.9969	0.96	0.9799	0.9528
0.0012	2.0	13126	0.0202	0.9977	0.9749	0.9992	0.9518	0.9759	0.9618
0.002	3.0	19689	0.0176	0.9978	0.9761	0.9985	0.9546	0.9773	0.9586
0.0	4.0	26252	0.0205	0.9977	0.9749	0.9992	0.9518	0.9759	0.961
0.0005	5.0	32815	0.0201	0.9978	0.9766	0.9985	0.9556	0.9778	0.9614

Framework versions

—Transformers 4.29.1
—Pytorch 1.9.0+cu111
—Datasets 2.10.1
—Tokenizers 0.13.2