ArabicNewSplits4_WithDuplicationsForScore5_FineTuningAraBERT_run2_AugV5_k9_task2_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: 1.0902
• Qwk: 0.4067
• Mse: 1.0902
• Rmse: 1.0441

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	0.0417	2	4.4173	-0.0237	4.4173	2.1017
No log	0.0833	4	2.4498	0.0247	2.4498	1.5652
No log	0.125	6	1.5197	-0.0455	1.5197	1.2328
No log	0.1667	8	1.4677	-0.0625	1.4677	1.2115
No log	0.2083	10	0.8768	0.0568	0.8768	0.9364
No log	0.25	12	0.7863	0.0884	0.7863	0.8867
No log	0.2917	14	0.7523	0.1063	0.7523	0.8674
No log	0.3333	16	0.7553	0.0973	0.7553	0.8691
No log	0.375	18	0.7735	0.1063	0.7735	0.8795
No log	0.4167	20	0.7517	0.1225	0.7517	0.8670
No log	0.4583	22	0.6964	0.2507	0.6964	0.8345
No log	0.5	24	0.7197	0.1311	0.7197	0.8484
No log	0.5417	26	0.7150	0.1764	0.7150	0.8456
No log	0.5833	28	0.6892	0.1607	0.6892	0.8302
No log	0.625	30	0.6608	0.2001	0.6608	0.8129
No log	0.6667	32	0.6475	0.2376	0.6475	0.8046
No log	0.7083	34	0.6397	0.2245	0.6397	0.7998
No log	0.75	36	0.7078	0.2050	0.7078	0.8413
No log	0.7917	38	0.7841	0.2531	0.7841	0.8855
No log	0.8333	40	0.7269	0.2819	0.7269	0.8526
No log	0.875	42	0.6747	0.1337	0.6747	0.8214
No log	0.9167	44	0.7817	0.2333	0.7817	0.8842
No log	0.9583	46	0.7720	0.2413	0.7720	0.8786
No log	1.0	48	0.6813	0.1631	0.6813	0.8254
No log	1.0417	50	0.6864	0.2447	0.6864	0.8285
No log	1.0833	52	0.7311	0.3253	0.7311	0.8550
No log	1.125	54	0.8147	0.3017	0.8147	0.9026
No log	1.1667	56	0.8891	0.2787	0.8891	0.9429
No log	1.2083	58	0.9366	0.3168	0.9366	0.9678
No log	1.25	60	1.0826	0.2601	1.0826	1.0405
No log	1.2917	62	1.0747	0.2482	1.0747	1.0367
No log	1.3333	64	1.0488	0.3251	1.0488	1.0241
No log	1.375	66	0.8421	0.3449	0.8421	0.9177
No log	1.4167	68	0.8139	0.3903	0.8139	0.9022
No log	1.4583	70	0.8803	0.3649	0.8803	0.9382
No log	1.5	72	1.1250	0.2931	1.1250	1.0606
No log	1.5417	74	1.4396	0.2408	1.4396	1.1999
No log	1.5833	76	1.3494	0.2812	1.3494	1.1616
No log	1.625	78	0.9649	0.3335	0.9649	0.9823
No log	1.6667	80	0.8841	0.3607	0.8841	0.9403
No log	1.7083	82	0.9526	0.3028	0.9526	0.9760
No log	1.75	84	1.2895	0.2341	1.2895	1.1356
No log	1.7917	86	1.4522	0.2966	1.4522	1.2051
No log	1.8333	88	1.2676	0.2502	1.2676	1.1259
No log	1.875	90	0.9752	0.3080	0.9752	0.9875
No log	1.9167	92	0.7651	0.4360	0.7651	0.8747
No log	1.9583	94	0.8250	0.4054	0.8250	0.9083
No log	2.0	96	1.0628	0.2698	1.0628	1.0309
No log	2.0417	98	1.3290	0.2655	1.3290	1.1528
No log	2.0833	100	1.2190	0.2231	1.2190	1.1041
No log	2.125	102	1.0285	0.2841	1.0285	1.0142
No log	2.1667	104	0.8736	0.3037	0.8736	0.9347
No log	2.2083	106	0.9113	0.2683	0.9113	0.9546
No log	2.25	108	1.1055	0.2702	1.1055	1.0514
No log	2.2917	110	1.2539	0.2550	1.2539	1.1198
No log	2.3333	112	1.6399	0.2327	1.6399	1.2806
No log	2.375	114	1.6292	0.2723	1.6292	1.2764
No log	2.4167	116	1.4828	0.2868	1.4828	1.2177
No log	2.4583	118	1.5385	0.2677	1.5385	1.2404
No log	2.5	120	1.4962	0.2734	1.4962	1.2232
No log	2.5417	122	1.3594	0.2936	1.3594	1.1659
No log	2.5833	124	1.4952	0.2767	1.4952	1.2228
No log	2.625	126	2.0613	0.2554	2.0613	1.4357
No log	2.6667	128	2.2674	0.2082	2.2674	1.5058
No log	2.7083	130	2.1021	0.2408	2.1021	1.4499
No log	2.75	132	1.6545	0.2888	1.6545	1.2863
No log	2.7917	134	1.4455	0.2726	1.4455	1.2023
No log	2.8333	136	1.2910	0.3274	1.2910	1.1362
No log	2.875	138	1.2018	0.3661	1.2018	1.0963
No log	2.9167	140	1.2694	0.3342	1.2694	1.1267
No log	2.9583	142	1.5178	0.2708	1.5178	1.2320
No log	3.0	144	1.8518	0.2553	1.8518	1.3608
No log	3.0417	146	1.7891	0.2661	1.7891	1.3376
No log	3.0833	148	1.5021	0.2588	1.5021	1.2256
No log	3.125	150	1.3086	0.3182	1.3086	1.1439
No log	3.1667	152	1.2895	0.3081	1.2895	1.1355
No log	3.2083	154	1.3919	0.2809	1.3919	1.1798
No log	3.25	156	1.3184	0.2816	1.3184	1.1482
No log	3.2917	158	1.3128	0.2512	1.3128	1.1458
No log	3.3333	160	1.3483	0.2075	1.3483	1.1612
No log	3.375	162	1.3510	0.2095	1.3510	1.1623
No log	3.4167	164	1.1869	0.3019	1.1869	1.0894
No log	3.4583	166	1.0937	0.3050	1.0937	1.0458
No log	3.5	168	0.9995	0.3673	0.9995	0.9998
No log	3.5417	170	1.0052	0.3879	1.0052	1.0026
No log	3.5833	172	1.0272	0.3499	1.0272	1.0135
No log	3.625	174	0.9792	0.4125	0.9792	0.9895
No log	3.6667	176	1.0537	0.3793	1.0537	1.0265
No log	3.7083	178	1.2484	0.3355	1.2484	1.1173
No log	3.75	180	1.5492	0.2546	1.5492	1.2447
No log	3.7917	182	1.6521	0.2720	1.6521	1.2853
No log	3.8333	184	1.4801	0.2855	1.4801	1.2166
No log	3.875	186	1.2539	0.3229	1.2539	1.1198
No log	3.9167	188	1.1059	0.3473	1.1059	1.0516
No log	3.9583	190	1.1560	0.3263	1.1560	1.0752
No log	4.0	192	1.1452	0.3371	1.1452	1.0701
No log	4.0417	194	1.1462	0.3511	1.1462	1.0706
No log	4.0833	196	1.1870	0.3405	1.1870	1.0895
No log	4.125	198	1.1610	0.3477	1.1610	1.0775
No log	4.1667	200	1.0759	0.3844	1.0759	1.0373
No log	4.2083	202	1.0223	0.4038	1.0223	1.0111
No log	4.25	204	1.0534	0.4144	1.0534	1.0264
No log	4.2917	206	1.1900	0.3411	1.1900	1.0909
No log	4.3333	208	1.4121	0.3274	1.4121	1.1883
No log	4.375	210	1.6525	0.3225	1.6525	1.2855
No log	4.4167	212	1.6344	0.3159	1.6344	1.2784
No log	4.4583	214	1.4872	0.3306	1.4872	1.2195
No log	4.5	216	1.2679	0.3471	1.2679	1.1260
No log	4.5417	218	1.1561	0.3494	1.1561	1.0752
No log	4.5833	220	1.1344	0.3614	1.1344	1.0651
No log	4.625	222	1.2030	0.3572	1.2030	1.0968
No log	4.6667	224	1.3371	0.3283	1.3371	1.1563
No log	4.7083	226	1.3107	0.3210	1.3107	1.1449
No log	4.75	228	1.2013	0.3733	1.2013	1.0960
No log	4.7917	230	1.2430	0.3637	1.2430	1.1149
No log	4.8333	232	1.1837	0.3554	1.1837	1.0880
No log	4.875	234	1.0612	0.3412	1.0612	1.0301
No log	4.9167	236	1.0536	0.3403	1.0536	1.0265
No log	4.9583	238	1.1206	0.3587	1.1206	1.0586
No log	5.0	240	1.2077	0.3361	1.2077	1.0990
No log	5.0417	242	1.2698	0.3073	1.2698	1.1268
No log	5.0833	244	1.2067	0.3554	1.2067	1.0985
No log	5.125	246	1.1705	0.3503	1.1705	1.0819
No log	5.1667	248	1.1929	0.3554	1.1929	1.0922
No log	5.2083	250	1.2307	0.3611	1.2307	1.1094
No log	5.25	252	1.2308	0.3419	1.2308	1.1094
No log	5.2917	254	1.2325	0.3661	1.2325	1.1102
No log	5.3333	256	1.1971	0.3578	1.1971	1.0941
No log	5.375	258	1.1494	0.3687	1.1494	1.0721
No log	5.4167	260	1.0915	0.375	1.0915	1.0447
No log	5.4583	262	1.1177	0.3741	1.1177	1.0572
No log	5.5	264	1.1909	0.3557	1.1909	1.0913
No log	5.5417	266	1.3502	0.3639	1.3502	1.1620
No log	5.5833	268	1.4706	0.2983	1.4706	1.2127
No log	5.625	270	1.4602	0.2983	1.4602	1.2084
No log	5.6667	272	1.4376	0.3030	1.4376	1.1990
No log	5.7083	274	1.3594	0.3206	1.3594	1.1659
No log	5.75	276	1.2784	0.3183	1.2784	1.1307
No log	5.7917	278	1.1265	0.3568	1.1265	1.0614
No log	5.8333	280	0.9985	0.4185	0.9985	0.9992
No log	5.875	282	0.9534	0.4235	0.9534	0.9764
No log	5.9167	284	0.9843	0.4250	0.9843	0.9921
No log	5.9583	286	1.1091	0.3779	1.1091	1.0532
No log	6.0	288	1.2532	0.3391	1.2532	1.1195
No log	6.0417	290	1.3187	0.3118	1.3187	1.1483
No log	6.0833	292	1.2778	0.3008	1.2778	1.1304
No log	6.125	294	1.1495	0.3777	1.1495	1.0722
No log	6.1667	296	1.0640	0.4235	1.0640	1.0315
No log	6.2083	298	1.0379	0.4150	1.0379	1.0188
No log	6.25	300	1.0553	0.4166	1.0553	1.0273
No log	6.2917	302	1.1229	0.3970	1.1229	1.0597
No log	6.3333	304	1.1673	0.3345	1.1673	1.0804
No log	6.375	306	1.1171	0.3957	1.1171	1.0569
No log	6.4167	308	1.0363	0.4217	1.0363	1.0180
No log	6.4583	310	0.9908	0.4235	0.9908	0.9954
No log	6.5	312	0.9639	0.4181	0.9639	0.9818
No log	6.5417	314	0.9771	0.4215	0.9771	0.9885
No log	6.5833	316	1.0182	0.4199	1.0182	1.0091
No log	6.625	318	1.0515	0.3520	1.0515	1.0254
No log	6.6667	320	1.0758	0.3357	1.0758	1.0372
No log	6.7083	322	1.0527	0.3944	1.0527	1.0260
No log	6.75	324	1.0173	0.4086	1.0173	1.0086
No log	6.7917	326	0.9910	0.4323	0.9910	0.9955
No log	6.8333	328	0.9632	0.4043	0.9632	0.9814
No log	6.875	330	0.9627	0.4043	0.9627	0.9812
No log	6.9167	332	0.9746	0.3929	0.9746	0.9872
No log	6.9583	334	0.9905	0.4357	0.9905	0.9952
No log	7.0	336	1.0400	0.4171	1.0400	1.0198
No log	7.0417	338	1.0677	0.4389	1.0677	1.0333
No log	7.0833	340	1.0770	0.4235	1.0770	1.0378
No log	7.125	342	1.1178	0.4220	1.1178	1.0573
No log	7.1667	344	1.1951	0.3500	1.1951	1.0932
No log	7.2083	346	1.2269	0.3471	1.2269	1.1076
No log	7.25	348	1.2165	0.3684	1.2165	1.1029
No log	7.2917	350	1.2199	0.3684	1.2199	1.1045
No log	7.3333	352	1.2170	0.3684	1.2170	1.1032
No log	7.375	354	1.2043	0.3684	1.2043	1.0974
No log	7.4167	356	1.2264	0.3525	1.2264	1.1074
No log	7.4583	358	1.2638	0.3366	1.2638	1.1242
No log	7.5	360	1.2443	0.3366	1.2443	1.1155
No log	7.5417	362	1.1990	0.3617	1.1990	1.0950
No log	7.5833	364	1.1681	0.3718	1.1681	1.0808
No log	7.625	366	1.1478	0.3775	1.1478	1.0714
No log	7.6667	368	1.0957	0.3894	1.0957	1.0467
No log	7.7083	370	1.0454	0.4268	1.0454	1.0225
No log	7.75	372	1.0207	0.4288	1.0207	1.0103
No log	7.7917	374	1.0170	0.4459	1.0170	1.0085
No log	7.8333	376	1.0416	0.4322	1.0416	1.0206
No log	7.875	378	1.0634	0.4235	1.0634	1.0312
No log	7.9167	380	1.0934	0.4336	1.0934	1.0457
No log	7.9583	382	1.1370	0.4063	1.1370	1.0663
No log	8.0	384	1.1781	0.3621	1.1781	1.0854
No log	8.0417	386	1.1701	0.3621	1.1701	1.0817
No log	8.0833	388	1.1248	0.3608	1.1248	1.0605
No log	8.125	390	1.0548	0.4140	1.0548	1.0270
No log	8.1667	392	0.9939	0.4395	0.9939	0.9970
No log	8.2083	394	0.9734	0.4288	0.9734	0.9866
No log	8.25	396	0.9756	0.4398	0.9756	0.9877
No log	8.2917	398	0.9976	0.4451	0.9976	0.9988
No log	8.3333	400	1.0341	0.4321	1.0341	1.0169
No log	8.375	402	1.0920	0.3704	1.0920	1.0450
No log	8.4167	404	1.1269	0.3528	1.1269	1.0616
No log	8.4583	406	1.1243	0.3704	1.1243	1.0603
No log	8.5	408	1.1141	0.3838	1.1141	1.0555
No log	8.5417	410	1.1192	0.3861	1.1192	1.0579
No log	8.5833	412	1.1184	0.3861	1.1184	1.0576
No log	8.625	414	1.1311	0.3757	1.1311	1.0635
No log	8.6667	416	1.1666	0.3499	1.1666	1.0801
No log	8.7083	418	1.1879	0.3468	1.1879	1.0899
No log	8.75	420	1.2132	0.3450	1.2132	1.1015
No log	8.7917	422	1.2359	0.3270	1.2359	1.1117
No log	8.8333	424	1.2582	0.3323	1.2582	1.1217
No log	8.875	426	1.2543	0.3323	1.2543	1.1200
No log	8.9167	428	1.2387	0.3270	1.2387	1.1130
No log	8.9583	430	1.2201	0.3187	1.2201	1.1046
No log	9.0	432	1.1943	0.3306	1.1943	1.0929
No log	9.0417	434	1.1768	0.3371	1.1768	1.0848
No log	9.0833	436	1.1747	0.3297	1.1747	1.0838
No log	9.125	438	1.1880	0.3306	1.1880	1.0899
No log	9.1667	440	1.1873	0.3306	1.1873	1.0897
No log	9.2083	442	1.1792	0.3297	1.1792	1.0859
No log	9.25	444	1.1650	0.3642	1.1650	1.0793
No log	9.2917	446	1.1515	0.3772	1.1515	1.0731
No log	9.3333	448	1.1386	0.3858	1.1386	1.0670
No log	9.375	450	1.1237	0.3850	1.1237	1.0601
No log	9.4167	452	1.1068	0.4025	1.1068	1.0520
No log	9.4583	454	1.0918	0.4134	1.0918	1.0449
No log	9.5	456	1.0870	0.4133	1.0870	1.0426
No log	9.5417	458	1.0908	0.4065	1.0908	1.0444
No log	9.5833	460	1.0947	0.4067	1.0947	1.0463
No log	9.625	462	1.0975	0.4067	1.0975	1.0476
No log	9.6667	464	1.0986	0.4067	1.0986	1.0481
No log	9.7083	466	1.0951	0.4067	1.0951	1.0465
No log	9.75	468	1.0911	0.4067	1.0911	1.0446
No log	9.7917	470	1.0900	0.4067	1.0900	1.0440
No log	9.8333	472	1.0924	0.4067	1.0924	1.0452
No log	9.875	474	1.0929	0.4067	1.0929	1.0454
No log	9.9167	476	1.0918	0.4067	1.0918	1.0449
No log	9.9583	478	1.0904	0.4067	1.0904	1.0442
No log	10.0	480	1.0902	0.4067	1.0902	1.0441

Framework versions

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