ArabicNewSplits6_WithDuplicationsForScore5_FineTuningAraBERT_run3_AugV5_k8_task5_organization

This model is a fine-tuned version of aubmindlab/bert-base-arabertv02 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9472
• Qwk: 0.6572
• Mse: 0.9472
• Rmse: 0.9732

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.0588	2	2.2410	0.0054	2.2410	1.4970
No log	0.1176	4	1.4262	0.1683	1.4262	1.1942
No log	0.1765	6	1.3351	0.1811	1.3351	1.1555
No log	0.2353	8	1.3595	0.2447	1.3595	1.1660
No log	0.2941	10	1.4207	0.2815	1.4207	1.1919
No log	0.3529	12	1.5887	0.3162	1.5887	1.2604
No log	0.4118	14	1.6525	0.3706	1.6525	1.2855
No log	0.4706	16	1.4709	0.3599	1.4709	1.2128
No log	0.5294	18	1.2775	0.2119	1.2775	1.1302
No log	0.5882	20	1.2413	0.1931	1.2413	1.1141
No log	0.6471	22	1.2151	0.2186	1.2151	1.1023
No log	0.7059	24	1.2149	0.1581	1.2149	1.1022
No log	0.7647	26	1.2609	0.1948	1.2609	1.1229
No log	0.8235	28	1.2970	0.1814	1.2970	1.1389
No log	0.8824	30	1.2903	0.1976	1.2903	1.1359
No log	0.9412	32	1.3614	0.3526	1.3614	1.1668
No log	1.0	34	1.5503	0.3543	1.5503	1.2451
No log	1.0588	36	1.6044	0.3579	1.6044	1.2666
No log	1.1176	38	1.3833	0.3655	1.3833	1.1761
No log	1.1765	40	1.2006	0.3203	1.2006	1.0957
No log	1.2353	42	1.2950	0.3104	1.2950	1.1380
No log	1.2941	44	1.3431	0.2616	1.3431	1.1589
No log	1.3529	46	1.2345	0.3333	1.2345	1.1111
No log	1.4118	48	1.1088	0.3383	1.1088	1.0530
No log	1.4706	50	1.1821	0.4150	1.1821	1.0872
No log	1.5294	52	1.3601	0.4219	1.3601	1.1662
No log	1.5882	54	1.4049	0.4268	1.4049	1.1853
No log	1.6471	56	1.2684	0.4200	1.2684	1.1262
No log	1.7059	58	1.0902	0.3832	1.0902	1.0441
No log	1.7647	60	1.0582	0.3860	1.0582	1.0287
No log	1.8235	62	1.0428	0.4165	1.0428	1.0212
No log	1.8824	64	1.1277	0.4774	1.1277	1.0619
No log	1.9412	66	1.2302	0.4849	1.2302	1.1091
No log	2.0	68	1.2562	0.4899	1.2562	1.1208
No log	2.0588	70	1.1621	0.4756	1.1621	1.0780
No log	2.1176	72	1.0155	0.5131	1.0155	1.0077
No log	2.1765	74	0.8810	0.5720	0.8810	0.9386
No log	2.2353	76	0.9033	0.4885	0.9033	0.9504
No log	2.2941	78	0.8985	0.4885	0.8985	0.9479
No log	2.3529	80	0.8334	0.5532	0.8334	0.9129
No log	2.4118	82	0.9225	0.5557	0.9225	0.9604
No log	2.4706	84	1.1607	0.4859	1.1607	1.0773
No log	2.5294	86	1.3384	0.5274	1.3384	1.1569
No log	2.5882	88	1.3146	0.5447	1.3146	1.1466
No log	2.6471	90	1.1593	0.5139	1.1593	1.0767
No log	2.7059	92	1.1147	0.5214	1.1147	1.0558
No log	2.7647	94	1.0521	0.5273	1.0521	1.0257
No log	2.8235	96	1.0592	0.5169	1.0592	1.0292
No log	2.8824	98	0.9796	0.5771	0.9796	0.9898
No log	2.9412	100	0.9813	0.5794	0.9813	0.9906
No log	3.0	102	0.9473	0.5954	0.9473	0.9733
No log	3.0588	104	0.8505	0.6405	0.8505	0.9222
No log	3.1176	106	0.7418	0.6641	0.7418	0.8613
No log	3.1765	108	0.7264	0.6641	0.7264	0.8523
No log	3.2353	110	0.7728	0.6411	0.7728	0.8791
No log	3.2941	112	0.8919	0.6732	0.8919	0.9444
No log	3.3529	114	1.0549	0.6257	1.0549	1.0271
No log	3.4118	116	1.0441	0.6097	1.0441	1.0218
No log	3.4706	118	0.9204	0.6291	0.9204	0.9594
No log	3.5294	120	0.8526	0.6666	0.8526	0.9234
No log	3.5882	122	0.8155	0.6685	0.8155	0.9031
No log	3.6471	124	0.8368	0.6646	0.8368	0.9148
No log	3.7059	126	0.9863	0.6500	0.9863	0.9931
No log	3.7647	128	1.1804	0.5765	1.1804	1.0864
No log	3.8235	130	1.3535	0.5607	1.3535	1.1634
No log	3.8824	132	1.2192	0.5952	1.2192	1.1042
No log	3.9412	134	1.0427	0.6383	1.0427	1.0211
No log	4.0	136	0.9447	0.6356	0.9447	0.9719
No log	4.0588	138	0.9900	0.6310	0.9900	0.9950
No log	4.1176	140	0.9692	0.6310	0.9692	0.9845
No log	4.1765	142	0.9083	0.6175	0.9083	0.9530
No log	4.2353	144	0.8522	0.6294	0.8522	0.9232
No log	4.2941	146	0.7636	0.6604	0.7636	0.8738
No log	4.3529	148	0.7740	0.6703	0.7740	0.8798
No log	4.4118	150	0.8112	0.6458	0.8112	0.9007
No log	4.4706	152	0.8167	0.6603	0.8167	0.9037
No log	4.5294	154	0.8925	0.6595	0.8925	0.9447
No log	4.5882	156	0.9631	0.6294	0.9631	0.9814
No log	4.6471	158	0.8806	0.6354	0.8806	0.9384
No log	4.7059	160	0.8007	0.6586	0.8007	0.8948
No log	4.7647	162	0.7733	0.6864	0.7733	0.8794
No log	4.8235	164	0.7274	0.6920	0.7274	0.8529
No log	4.8824	166	0.6985	0.7026	0.6985	0.8358
No log	4.9412	168	0.7359	0.6928	0.7359	0.8579
No log	5.0	170	0.7402	0.6899	0.7402	0.8603
No log	5.0588	172	0.7525	0.6985	0.7525	0.8675
No log	5.1176	174	0.7314	0.6876	0.7314	0.8552
No log	5.1765	176	0.7162	0.7137	0.7162	0.8463
No log	5.2353	178	0.7282	0.7222	0.7282	0.8533
No log	5.2941	180	0.7551	0.6881	0.7551	0.8690
No log	5.3529	182	0.7804	0.6413	0.7804	0.8834
No log	5.4118	184	0.7713	0.6856	0.7713	0.8782
No log	5.4706	186	0.7768	0.6848	0.7768	0.8814
No log	5.5294	188	0.7644	0.6761	0.7644	0.8743
No log	5.5882	190	0.8121	0.6779	0.8121	0.9012
No log	5.6471	192	0.8174	0.6845	0.8174	0.9041
No log	5.7059	194	0.8114	0.6893	0.8114	0.9008
No log	5.7647	196	0.8200	0.6807	0.8200	0.9055
No log	5.8235	198	0.9026	0.6883	0.9026	0.9500
No log	5.8824	200	1.0158	0.6625	1.0158	1.0079
No log	5.9412	202	1.1631	0.6233	1.1631	1.0785
No log	6.0	204	1.1985	0.6040	1.1985	1.0948
No log	6.0588	206	1.0949	0.6176	1.0949	1.0464
No log	6.1176	208	0.9427	0.6752	0.9427	0.9709
No log	6.1765	210	0.8763	0.6669	0.8763	0.9361
No log	6.2353	212	0.8317	0.6694	0.8317	0.9120
No log	6.2941	214	0.8019	0.6649	0.8019	0.8955
No log	6.3529	216	0.7525	0.6914	0.7525	0.8675
No log	6.4118	218	0.7254	0.6972	0.7254	0.8517
No log	6.4706	220	0.7208	0.6843	0.7208	0.8490
No log	6.5294	222	0.6890	0.6974	0.6890	0.8301
No log	6.5882	224	0.6791	0.6884	0.6791	0.8241
No log	6.6471	226	0.6727	0.6975	0.6727	0.8202
No log	6.7059	228	0.6852	0.6884	0.6852	0.8278
No log	6.7647	230	0.7278	0.7089	0.7278	0.8531
No log	6.8235	232	0.8029	0.7052	0.8029	0.8960
No log	6.8824	234	0.9083	0.6789	0.9083	0.9530
No log	6.9412	236	1.0407	0.6793	1.0407	1.0202
No log	7.0	238	1.0761	0.6618	1.0761	1.0374
No log	7.0588	240	1.0426	0.6648	1.0426	1.0211
No log	7.1176	242	0.9463	0.6734	0.9463	0.9728
No log	7.1765	244	0.8273	0.6616	0.8273	0.9095
No log	7.2353	246	0.7889	0.6789	0.7889	0.8882
No log	7.2941	248	0.7846	0.6862	0.7846	0.8858
No log	7.3529	250	0.7991	0.6692	0.7991	0.8939
No log	7.4118	252	0.8409	0.6684	0.8409	0.9170
No log	7.4706	254	0.8476	0.6765	0.8476	0.9207
No log	7.5294	256	0.8581	0.6552	0.8581	0.9263
No log	7.5882	258	0.8478	0.6761	0.8478	0.9208
No log	7.6471	260	0.8206	0.6831	0.8206	0.9058
No log	7.7059	262	0.8159	0.6831	0.8159	0.9032
No log	7.7647	264	0.7828	0.7106	0.7828	0.8848
No log	7.8235	266	0.7697	0.7070	0.7697	0.8773
No log	7.8824	268	0.7783	0.7106	0.7783	0.8822
No log	7.9412	270	0.7666	0.7070	0.7666	0.8756
No log	8.0	272	0.7744	0.7070	0.7744	0.8800
No log	8.0588	274	0.8117	0.6831	0.8117	0.9009
No log	8.1176	276	0.8488	0.6859	0.8488	0.9213
No log	8.1765	278	0.8737	0.6504	0.8737	0.9347
No log	8.2353	280	0.8660	0.6547	0.8660	0.9306
No log	8.2941	282	0.8460	0.6458	0.8460	0.9198
No log	8.3529	284	0.8290	0.6658	0.8290	0.9105
No log	8.4118	286	0.8305	0.6475	0.8305	0.9113
No log	8.4706	288	0.8560	0.6539	0.8560	0.9252
No log	8.5294	290	0.8922	0.6626	0.8922	0.9445
No log	8.5882	292	0.9079	0.6644	0.9079	0.9528
No log	8.6471	294	0.9377	0.6539	0.9377	0.9684
No log	8.7059	296	0.9662	0.6605	0.9662	0.9830
No log	8.7647	298	0.9818	0.6703	0.9818	0.9908
No log	8.8235	300	0.9761	0.6703	0.9761	0.9880
No log	8.8824	302	0.9545	0.6572	0.9545	0.9770
No log	8.9412	304	0.9306	0.6572	0.9306	0.9647
No log	9.0	306	0.9120	0.6661	0.9120	0.9550
No log	9.0588	308	0.8969	0.6568	0.8969	0.9470
No log	9.1176	310	0.8878	0.6584	0.8878	0.9422
No log	9.1765	312	0.8786	0.6474	0.8786	0.9373
No log	9.2353	314	0.8622	0.6558	0.8622	0.9285
No log	9.2941	316	0.8532	0.6513	0.8532	0.9237
No log	9.3529	318	0.8501	0.6658	0.8501	0.9220
No log	9.4118	320	0.8558	0.6498	0.8558	0.9251
No log	9.4706	322	0.8691	0.6474	0.8691	0.9323
No log	9.5294	324	0.8856	0.6668	0.8856	0.9411
No log	9.5882	326	0.9066	0.6628	0.9066	0.9522
No log	9.6471	328	0.9287	0.6572	0.9287	0.9637
No log	9.7059	330	0.9404	0.6572	0.9404	0.9698
No log	9.7647	332	0.9449	0.6572	0.9449	0.9721
No log	9.8235	334	0.9456	0.6572	0.9456	0.9724
No log	9.8824	336	0.9467	0.6572	0.9467	0.9730
No log	9.9412	338	0.9476	0.6572	0.9476	0.9734
No log	10.0	340	0.9472	0.6572	0.9472	0.9732

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu118
• Datasets 2.21.0
• Tokenizers 0.19.1