Modelpublic

Arvnd03/Hate-Speech-Detection-Tweets-RoBERTa-base

sourceHugging Facemitupdated 3y agoView on Hugging Face

1likes8downloads

Model Card

Hate-Speech-Detection-Tweets-RoBERTa-base

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

—Loss: 0.1037
—Accuracy: 0.9904
—F1: 0.9884

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: 16
—evalbatchsize: 16
—seed: 42
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.0694	1.0	2558	0.0600	0.9836	0.9801
0.0556	2.0	5116	0.0657	0.9862	0.9832
0.0316	3.0	7674	0.0685	0.9852	0.9822
0.0218	4.0	10232	0.0831	0.9878	0.9851
0.016	5.0	12790	0.0769	0.9877	0.9850
0.0082	6.0	15348	0.0654	0.9894	0.9873
0.0057	7.0	17906	0.0923	0.9867	0.9840
0.006	8.0	20464	0.1143	0.9875	0.9850
0.0006	9.0	23022	0.1100	0.9896	0.9875
0.0034	10.0	25580	0.1037	0.9904	0.9884
0.0019	11.0	28138	0.1134	0.9899	0.9878
0.0038	12.0	30696	0.1076	0.9898	0.9877
0.0	13.0	33254	0.1252	0.9896	0.9874
0.0	14.0	35812	0.1255	0.9892	0.9869
0.0008	15.0	38370	0.1161	0.9902	0.9882

Framework versions

—Transformers 4.26.1
—Pytorch 2.0.1
—Datasets 2.10.1
—Tokenizers 0.13.3