Modelpublic

AIWizards/MultiPRIDE-DualEncoder-LPFT-it

sourceHugging Faceapache-2.0updated 9mo agoView on Hugging Face

0likes15downloads

Model Card

MultiPRIDE-DualEncoder-LPFT-it

This model is a fine-tuned version of nickprock/setfit-italian-hate-speech on the None dataset. It achieves the following results on the evaluation set:

—Loss: 0.0105
—Accuracy: 0.9693
—F1: 0.9180
—Precision: 0.9333
—Recall: 0.9032

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
—trainbatchsize: 8
—evalbatchsize: 8
—seed: 1337
—optimizer: Use adamwtorchfused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
—lrschedulertype: linear
—num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.1597	1.0	95	0.1206	0.8528	0.5385	0.6667	0.4516
0.1218	2.0	190	0.0621	0.8834	0.7077	0.6765	0.7419
0.0744	3.0	285	0.0270	0.9387	0.8438	0.8182	0.8710
0.0431	4.0	380	0.0167	0.9632	0.9032	0.9032	0.9032
0.0393	5.0	475	0.0128	0.9571	0.8889	0.875	0.9032
0.0223	6.0	570	0.0116	0.9693	0.9180	0.9333	0.9032
0.0432	7.0	665	0.0108	0.9693	0.9180	0.9333	0.9032
0.0348	8.0	760	0.0105	0.9693	0.9180	0.9333	0.9032
0.035	9.0	855	0.0105	0.9693	0.9180	0.9333	0.9032

Framework versions

—Transformers 4.57.3
—Pytorch 2.9.1+cu128
—Datasets 4.4.1
—Tokenizers 0.22.1