arabic_fake_news_classifier

khulud03/arabic_fake_news_classifier

arabic_fake_news_classifier is a text classification model from khulud03. Use it when you need a label for a piece of text. It is set up for transformers.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

18% of all-time downloads

All-time downloads

Public

Parameters

135M

541 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors541 MB · 100%

At a glance

Task: Text Classification
Library: transformers
Model type: bert
Access: Public
Created: Aug 6, 2025
Updated: Aug 6, 2025
SHA: 82bccb23

Try a prompt

Base models

aubmindlab/bert-base-arabertv2

Model card

From the Hugging Face model README

arabic_fake_news_classifier

This model is a fine-tuned version of aubmindlab/bert-base-arabertv2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0619
Accuracy: 0.9905
F1: 0.9905
Precision: 0.9907
Recall: 0.9905

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
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Accuracy	F1	Validation Loss	Precision	Recall
0.3979	0.0231	50	0.8841	0.8828	0.2744	0.9022	0.8841
0.1868	0.0463	100	0.9099	0.9092	0.2673	0.9236	0.9099
0.1183	0.0694	150	0.9597	0.9596	0.1396	0.9627	0.9597
0.0875	0.0926	200	0.9707	0.9707	0.0918	0.9723	0.9707
0.0473	0.1157	250	0.9744	0.9744	0.0946	0.9756	0.9744
0.035	0.1389	300	0.9843	0.9843	0.0679	0.9847	0.9843
0.0548	0.1620	350	0.9946	0.9946	0.0217	0.9946	0.9946
0.0623	0.1852	400	0.9775	0.9775	0.0923	0.9784	0.9775
0.047	0.2083	450	0.9598	0.9598	0.1832	0.9628	0.9598
0.0326	0.2315	500	0.9579	0.9578	0.1770	0.9611	0.9579
0.0402	0.2546	550	0.9736	0.9736	0.1148	0.9749	0.9736
0.0261	0.2778	600	0.9904	0.9904	0.0463	0.9905	0.9904
0.0685	0.3009	650	0.9793	0.9793	0.0698	0.9800	0.9793
0.037	0.3241	700	0.9862	0.9862	0.0619	0.9866	0.9862
0.0364	0.3472	750	0.9919	0.9919	0.0301	0.9920	0.9919
0.0424	0.3704	800	0.9896	0.9896	0.0507	0.9897	0.9896
0.0428	0.3935	850	0.9861	0.9861	0.0733	0.9864	0.9861
0.0213	0.4167	900	0.9838	0.9838	0.0741	0.9843	0.9838
0.0585	0.4398	950	0.9766	0.9766	0.1054	0.9776	0.9766
0.0695	0.4630	1000	0.9733	0.9732	0.1113	0.9745	0.9733
0.0373	0.4861	1050	0.9941	0.9941	0.0280	0.9941	0.9941
0.0181	0.5093	1100	0.9897	0.9897	0.0489	0.9899	0.9897
0.0273	0.5324	1150	0.9871	0.9871	0.0694	0.9875	0.9871
0.0021	0.5556	1200	0.9929	0.9929	0.0409	0.9930	0.9929
0.04	0.5787	1250	0.9750	0.9750	0.1153	0.9762	0.9750
0.018	0.6019	1300	0.9889	0.9889	0.0575	0.9891	0.9889
0.0154	0.625	1350	0.9458	0.9457	0.3140	0.9511	0.9458
0.0433	0.6481	1400	0.9954	0.9954	0.0191	0.9954	0.9954
0.0231	0.6713	1450	0.9819	0.9819	0.0938	0.9826	0.9819
0.0161	0.6944	1500	0.9871	0.9871	0.0714	0.9875	0.9871
0.0197	0.7176	1550	0.9890	0.9890	0.0583	0.9892	0.9890
0.0345	0.7407	1600	0.9777	0.9776	0.1152	0.9786	0.9777
0.0046	0.7639	1650	0.9818	0.9818	0.0991	0.9825	0.9818
0.0347	0.7870	1700	0.9673	0.9673	0.1960	0.9693	0.9673
0.0176	0.8102	1750	0.9830	0.9830	0.0920	0.9835	0.9830
0.0267	0.8333	1800	0.9544	0.9543	0.1870	0.9582	0.9544
0.0156	0.8565	1850	0.9867	0.9867	0.0481	0.9870	0.9867
0.0291	0.8796	1900	0.9601	0.9600	0.1608	0.9630	0.9601
0.0362	0.9028	1950	0.9560	0.9559	0.2116	0.9596	0.9560
0.0196	0.9259	2000	0.9947	0.9947	0.0281	0.9947	0.9947
0.0215	0.9491	2050	0.9937	0.9937	0.0267	0.9938	0.9937
0.0105	0.9722	2100	0.9936	0.9936	0.0365	0.9937	0.9936
0.0313	0.9954	2150	0.9890	0.9890	0.0558	0.9892	0.9890
0.0102	1.0185	2200	0.9891	0.9891	0.0558	0.9893	0.9891
0.0354	1.0417	2250	0.9871	0.9871	0.0559	0.9874	0.9871
0.0155	1.0648	2300	0.9949	0.9949	0.0304	0.9950	0.9949
0.013	1.0880	2350	0.9811	0.9811	0.1033	0.9818	0.9811
0.0018	1.1111	2400	0.9672	0.9672	0.2012	0.9692	0.9672
0.0113	1.1343	2450	0.9787	0.9787	0.1234	0.9796	0.9787
0.0098	1.1574	2500	0.9919	0.9919	0.0453	0.9920	0.9919
0.0284	1.1806	2550	0.9905	0.9905	0.0489	0.9907	0.9905
0.015	1.2037	2600	0.9947	0.9947	0.0245	0.9947	0.9947
0.027	1.2269	2650	0.9895	0.9895	0.0480	0.9897	0.9895
0.0004	1.25	2700	0.9933	0.9933	0.0307	0.9934	0.9933
0.004	1.2731	2750	0.9914	0.9914	0.0461	0.9916	0.9914
0.0132	1.2963	2800	0.9825	0.9825	0.0934	0.9831	0.9825
0.0127	1.3194	2850	0.9855	0.9855	0.0705	0.9859	0.9855
0.0001	1.3426	2900	0.9917	0.9917	0.0462	0.9918	0.9917
0.0041	1.3657	2950	0.9893	0.9893	0.0535	0.9896	0.9893
0.0005	1.3889	3000	0.9889	0.9889	0.0619	0.9891	0.9889
0.009	1.4120	3050	0.9559	0.9558	0.2691	0.9595	0.9559
0.0082	1.4352	3100	0.9739	0.9739	0.1588	0.9752	0.9739
0.0393	1.4583	3150	0.9679	0.9679	0.1620	0.9699	0.9679
0.0161	1.4815	3200	0.9947	0.9947	0.0220	0.9947	0.9947
0.0004	1.5046	3250	0.9858	0.9858	0.0780	0.9862	0.9858
0.0064	1.5278	3300	0.9656	0.9656	0.1917	0.9678	0.9656
0.01	1.5509	3350	0.9913	0.9913	0.0519	0.9915	0.9913
0.0202	1.5741	3400	0.9946	0.9946	0.0257	0.9946	0.9946
0.0001	1.5972	3450	0.9920	0.9920	0.0421	0.9921	0.9920
0.0034	1.6204	3500	0.9955	0.9955	0.0267	0.9955	0.9955
0.0148	1.6435	3550	0.9907	0.9907	0.0524	0.9909	0.9907
0.003	1.6667	3600	0.9934	0.9934	0.0418	0.9935	0.9934
0.0003	1.6898	3650	0.9950	0.9950	0.0279	0.9951	0.9950
0.0001	1.7130	3700	0.9742	0.9742	0.1554	0.9754	0.9742
0.0001	1.7361	3750	0.9838	0.9838	0.1019	0.9843	0.9838
0.0001	1.7593	3800	0.9859	0.9859	0.0894	0.9863	0.9859
0.0175	1.7824	3850	0.9617	0.9616	0.2492	0.9644	0.9617
0.0004	1.8056	3900	0.9934	0.9934	0.0413	0.9935	0.9934
0.0098	1.8287	3950	0.9942	0.9942	0.0362	0.9943	0.9942
0.0098	1.8519	4000	0.9817	0.9817	0.1047	0.9824	0.9817
0.007	1.875	4050	0.9932	0.9932	0.0378	0.9933	0.9932
0.0006	1.8981	4100	0.9905	0.9905	0.0517	0.9907	0.9905
0.0	1.9213	4150	0.9867	0.9867	0.0767	0.9870	0.9867
0.0	1.9444	4200	0.9867	0.9867	0.0808	0.9870	0.9867
0.0007	1.9676	4250	0.9849	0.9849	0.1021	0.9854	0.9849
0.0184	1.9907	4300	0.9862	0.9862	0.0709	0.9866	0.9862
0.0078	2.0139	4350	0.9951	0.9951	0.0252	0.9952	0.9951
0.0001	2.0370	4400	0.9847	0.9847	0.0962	0.9852	0.9847
0.0054	2.0602	4450	0.9651	0.9651	0.2915	0.9674	0.9651
0.0356	2.0833	4500	0.9927	0.9927	0.0351	0.9928	0.9927
0.0334	2.1065	4550	0.9867	0.9867	0.0712	0.9870	0.9867
0.0611	2.1296	4600	0.9846	0.9846	0.0840	0.9850	0.9846
0.0056	2.1528	4650	0.9939	0.9939	0.0402	0.9939	0.9939
0.0391	2.1759	4700	0.9447	0.9445	0.3091	0.9502	0.9447
0.0221	2.1991	4750	0.9912	0.9912	0.0489	0.9914	0.9912
0.0271	2.2222	4800	0.8970	0.8958	0.5400	0.9146	0.8970
0.0138	2.2454	4850	0.9936	0.9936	0.0356	0.9937	0.9936
0.0081	2.2685	4900	0.9737	0.9737	0.1532	0.9750	0.9737
0.0053	2.2917	4950	0.9697	0.9696	0.1791	0.9714	0.9697
0.0009	2.3148	5000	0.9856	0.9856	0.0890	0.9860	0.9856
0.0033	2.3380	5050	0.9946	0.9946	0.0339	0.9946	0.9946
0.0	2.3611	5100	0.9860	0.9860	0.0941	0.9864	0.9860
0.0184	2.3843	5150	0.9969	0.9969	0.0207	0.9969	0.9969
0.0132	2.4074	5200	0.9966	0.9966	0.0210	0.9967	0.9966
0.0067	2.4306	5250	0.9736	0.9736	0.1886	0.9749	0.9736
0.0258	2.4537	5300	0.9892	0.9892	0.0601	0.9894	0.9892
0.0208	2.4769	5350	0.9968	0.9968	0.0140	0.9968	0.9968
0.0058	2.5	5400	0.9920	0.9920	0.0522	0.9921	0.9920
0.0113	2.5231	5450	0.9973	0.9973	0.0188	0.9973	0.9973
0.0093	2.5463	5500	0.9904	0.9904	0.0642	0.9906	0.9904
0.0119	2.5694	5550	0.9963	0.9963	0.0237	0.9963	0.9963
0.0091	2.5926	5600	0.9834	0.9834	0.1055	0.9840	0.9834
0.0159	2.6157	5650	0.9897	0.9897	0.0671	0.9899	0.9897
0.0092	2.6389	5700	0.9841	0.9841	0.0979	0.9846	0.9841
0.0043	2.6620	5750	0.9887	0.9887	0.0727	0.9889	0.9887
0.0007	2.6852	5800	0.9919	0.9919	0.0536	0.9920	0.9919
0.0	2.7083	5850	0.9918	0.9918	0.0539	0.9919	0.9918
0.0043	2.7315	5900	0.9904	0.9904	0.0644	0.9906	0.9904
0.0	2.7546	5950	0.9920	0.9920	0.0508	0.9921	0.9920
0.0136	2.7778	6000	0.9832	0.9832	0.1162	0.9838	0.9832
0.0	2.8009	6050	0.9935	0.9935	0.0440	0.9936	0.9935
0.0122	2.8241	6100	0.9909	0.9909	0.0614	0.9910	0.9909
0.0001	2.8472	6150	0.9896	0.9896	0.0693	0.9898	0.9896
0.012	2.8704	6200	0.9831	0.9831	0.1143	0.9836	0.9831
0.027	2.8935	6250	0.9794	0.9794	0.1107	0.9802	0.9794
0.0231	2.9167	6300	0.9686	0.9686	0.1904	0.9705	0.9686
0.0125	2.9398	6350	0.9907	0.9907	0.0589	0.9909	0.9907
0.0064	2.9630	6400	0.9845	0.9845	0.1102	0.9850	0.9845
0.0069	2.9861	6450	0.9971	0.9971	0.0134	0.9971	0.9971

Framework versions

Transformers 4.53.3
Pytorch 2.6.0+cu124
Datasets 4.0.0
Tokenizers 0.21.2

Task: Text Classification
Library: transformers
Type: bert
Created: Aug 6, 2025
Updated: Aug 6, 2025