Modelpublic

Sidhartha2004/finetuned_cyberbullying_muril

sourceHugging Faceapache-2.0updated 8mo agoView on Hugging Face

1likes13downloads

Model Card

finetunedcyberbullyingmuril

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

—Loss: 0.0078
—Accuracy: 0.9987
—F1: 0.9988
—Precision: 0.9993
—Recall: 0.9984
—Specificity: 0.9991
—Roc Auc: 1.0000

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: 5e-05
—trainbatchsize: 256
—evalbatchsize: 512
—seed: 42
—optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
—lrschedulertype: cosine
—lrschedulerwarmup_ratio: 0.03
—num_epochs: 2
—mixedprecisiontraining: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Specificity	Roc Auc
0.0121	0.2559	500	0.0102	0.9955	0.9961	0.9980	0.9941	0.9974	0.9999
0.0094	0.5118	1000	0.0095	0.9972	0.9975	0.9994	0.9956	0.9992	0.9999
0.0083	0.7677	1500	0.0085	0.9983	0.9985	0.9996	0.9975	0.9994	0.9998
0.008	1.0235	2000	0.0083	0.9985	0.9987	0.9992	0.9982	0.9989	0.9999
0.0077	1.2794	2500	0.0077	0.999	0.9991	0.9996	0.9986	0.9995	1.0000
0.0075	1.5353	3000	0.0078	0.9989	0.9991	0.9996	0.9985	0.9994	1.0000
0.0073	1.7912	3500	0.0078	0.9989	0.9990	0.9996	0.9985	0.9994	1.0000

Framework versions

—Transformers 4.57.1
—Pytorch 2.8.0+cu126
—Datasets 4.4.2
—Tokenizers 0.22.1