ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run3_AugV5_k1_task1_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: 1.3248
• Qwk: 0.4031
• Mse: 1.3248
• Rmse: 1.1510

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: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.3333	2	5.0895	-0.0091	5.0895	2.2560
No log	0.6667	4	3.0733	0.1175	3.0733	1.7531
No log	1.0	6	1.6651	0.1056	1.6651	1.2904
No log	1.3333	8	1.3147	0.1664	1.3147	1.1466
No log	1.6667	10	1.2103	0.1497	1.2103	1.1001
No log	2.0	12	1.3751	0.2661	1.3751	1.1726
No log	2.3333	14	1.7707	0.3052	1.7707	1.3307
No log	2.6667	16	1.6462	0.2303	1.6462	1.2830
No log	3.0	18	1.5379	0.2403	1.5379	1.2401
No log	3.3333	20	1.7061	0.3132	1.7061	1.3062
No log	3.6667	22	1.4518	0.3779	1.4518	1.2049
No log	4.0	24	1.3071	0.3717	1.3071	1.1433
No log	4.3333	26	1.3379	0.4473	1.3379	1.1567
No log	4.6667	28	1.5017	0.3790	1.5017	1.2254
No log	5.0	30	1.4230	0.3876	1.4230	1.1929
No log	5.3333	32	1.4290	0.3962	1.4290	1.1954
No log	5.6667	34	1.6503	0.2838	1.6503	1.2846
No log	6.0	36	1.7907	0.2553	1.7907	1.3382
No log	6.3333	38	1.5717	0.3356	1.5717	1.2537
No log	6.6667	40	1.2850	0.4264	1.2850	1.1336
No log	7.0	42	1.1840	0.4271	1.1840	1.0881
No log	7.3333	44	1.2842	0.4210	1.2842	1.1332
No log	7.6667	46	1.9551	0.2358	1.9551	1.3983
No log	8.0	48	2.3899	0.1934	2.3899	1.5459
No log	8.3333	50	2.3391	0.2260	2.3391	1.5294
No log	8.6667	52	1.7842	0.3031	1.7842	1.3357
No log	9.0	54	1.5225	0.3757	1.5225	1.2339
No log	9.3333	56	1.2642	0.3787	1.2642	1.1244
No log	9.6667	58	1.4685	0.3494	1.4685	1.2118
No log	10.0	60	1.8642	0.2449	1.8642	1.3654
No log	10.3333	62	1.8220	0.2543	1.8220	1.3498
No log	10.6667	64	1.3729	0.3954	1.3729	1.1717
No log	11.0	66	1.3825	0.4044	1.3825	1.1758
No log	11.3333	68	1.5765	0.3199	1.5765	1.2556
No log	11.6667	70	1.8969	0.3071	1.8969	1.3773
No log	12.0	72	1.6050	0.3482	1.6050	1.2669
No log	12.3333	74	1.2263	0.4833	1.2263	1.1074
No log	12.6667	76	1.0504	0.5280	1.0504	1.0249
No log	13.0	78	1.1090	0.4851	1.1090	1.0531
No log	13.3333	80	1.2646	0.4755	1.2646	1.1245
No log	13.6667	82	1.3019	0.4276	1.3019	1.1410
No log	14.0	84	1.1274	0.4595	1.1274	1.0618
No log	14.3333	86	1.1816	0.4364	1.1816	1.0870
No log	14.6667	88	1.5146	0.3148	1.5146	1.2307
No log	15.0	90	1.5089	0.3388	1.5089	1.2284
No log	15.3333	92	1.1168	0.4405	1.1168	1.0568
No log	15.6667	94	1.0362	0.4514	1.0362	1.0180
No log	16.0	96	1.2425	0.4184	1.2425	1.1147
No log	16.3333	98	1.4119	0.3721	1.4119	1.1882
No log	16.6667	100	1.4115	0.3618	1.4115	1.1881
No log	17.0	102	1.1990	0.4184	1.1990	1.0950
No log	17.3333	104	1.2707	0.4104	1.2707	1.1272
No log	17.6667	106	1.2005	0.4430	1.2005	1.0957
No log	18.0	108	1.2784	0.4029	1.2784	1.1306
No log	18.3333	110	1.2863	0.3846	1.2863	1.1342
No log	18.6667	112	1.5427	0.3763	1.5427	1.2420
No log	19.0	114	1.5108	0.3649	1.5108	1.2292
No log	19.3333	116	1.2645	0.3763	1.2645	1.1245
No log	19.6667	118	1.1184	0.4199	1.1184	1.0576
No log	20.0	120	1.2048	0.3908	1.2048	1.0976
No log	20.3333	122	1.4423	0.3562	1.4423	1.2010
No log	20.6667	124	1.4974	0.3453	1.4974	1.2237
No log	21.0	126	1.3911	0.3892	1.3911	1.1794
No log	21.3333	128	1.1774	0.4864	1.1774	1.0851
No log	21.6667	130	1.1005	0.4772	1.1005	1.0490
No log	22.0	132	1.0675	0.4943	1.0675	1.0332
No log	22.3333	134	1.1074	0.5101	1.1074	1.0523
No log	22.6667	136	1.3124	0.4453	1.3124	1.1456
No log	23.0	138	1.4632	0.3475	1.4632	1.2096
No log	23.3333	140	1.3685	0.3676	1.3685	1.1698
No log	23.6667	142	1.2025	0.4025	1.2025	1.0966
No log	24.0	144	1.2813	0.4046	1.2813	1.1320
No log	24.3333	146	1.5137	0.3631	1.5137	1.2303
No log	24.6667	148	1.5862	0.3663	1.5862	1.2594
No log	25.0	150	1.3480	0.3787	1.3480	1.1611
No log	25.3333	152	1.0538	0.4836	1.0538	1.0265
No log	25.6667	154	1.0311	0.4572	1.0311	1.0154
No log	26.0	156	1.1918	0.3947	1.1918	1.0917
No log	26.3333	158	1.7285	0.3465	1.7285	1.3147
No log	26.6667	160	2.0376	0.3438	2.0376	1.4274
No log	27.0	162	1.8650	0.3389	1.8650	1.3656
No log	27.3333	164	1.4452	0.4300	1.4452	1.2021
No log	27.6667	166	1.0518	0.5113	1.0518	1.0256
No log	28.0	168	0.9353	0.4769	0.9353	0.9671
No log	28.3333	170	0.9262	0.4712	0.9262	0.9624
No log	28.6667	172	1.0267	0.5051	1.0267	1.0133
No log	29.0	174	1.3131	0.3927	1.3131	1.1459
No log	29.3333	176	1.7112	0.3163	1.7112	1.3081
No log	29.6667	178	1.7809	0.3185	1.7809	1.3345
No log	30.0	180	1.5704	0.3361	1.5704	1.2532
No log	30.3333	182	1.2288	0.4566	1.2288	1.1085
No log	30.6667	184	1.0735	0.4825	1.0735	1.0361
No log	31.0	186	1.0329	0.4891	1.0329	1.0163
No log	31.3333	188	1.0994	0.5043	1.0994	1.0485
No log	31.6667	190	1.1855	0.4859	1.1855	1.0888
No log	32.0	192	1.2046	0.4376	1.2046	1.0975
No log	32.3333	194	1.2442	0.4312	1.2442	1.1154
No log	32.6667	196	1.1991	0.4283	1.1991	1.0951
No log	33.0	198	1.1183	0.5043	1.1183	1.0575
No log	33.3333	200	1.1438	0.5179	1.1438	1.0695
No log	33.6667	202	1.2516	0.4522	1.2516	1.1188
No log	34.0	204	1.3508	0.4387	1.3508	1.1622
No log	34.3333	206	1.3368	0.4534	1.3368	1.1562
No log	34.6667	208	1.2493	0.4651	1.2493	1.1177
No log	35.0	210	1.1581	0.4776	1.1581	1.0761
No log	35.3333	212	1.1351	0.4770	1.1351	1.0654
No log	35.6667	214	1.1416	0.4947	1.1416	1.0685
No log	36.0	216	1.1793	0.4777	1.1793	1.0860
No log	36.3333	218	1.2048	0.4771	1.2048	1.0977
No log	36.6667	220	1.3286	0.4194	1.3286	1.1527
No log	37.0	222	1.4992	0.3802	1.4992	1.2244
No log	37.3333	224	1.4361	0.4062	1.4361	1.1984
No log	37.6667	226	1.3562	0.4159	1.3562	1.1646
No log	38.0	228	1.1627	0.4913	1.1627	1.0783
No log	38.3333	230	1.1224	0.4921	1.1224	1.0594
No log	38.6667	232	1.1288	0.5005	1.1288	1.0624
No log	39.0	234	1.2386	0.4705	1.2386	1.1129
No log	39.3333	236	1.1850	0.4985	1.1850	1.0886
No log	39.6667	238	1.1562	0.4879	1.1562	1.0753
No log	40.0	240	1.0968	0.4612	1.0968	1.0473
No log	40.3333	242	1.0900	0.4868	1.0900	1.0440
No log	40.6667	244	1.1384	0.4809	1.1384	1.0670
No log	41.0	246	1.2809	0.4539	1.2809	1.1317
No log	41.3333	248	1.3777	0.3979	1.3777	1.1738
No log	41.6667	250	1.4410	0.3755	1.4410	1.2004
No log	42.0	252	1.3941	0.3848	1.3941	1.1807
No log	42.3333	254	1.2368	0.4460	1.2368	1.1121
No log	42.6667	256	1.1613	0.4573	1.1613	1.0776
No log	43.0	258	1.0242	0.5002	1.0242	1.0120
No log	43.3333	260	0.9954	0.5058	0.9954	0.9977
No log	43.6667	262	1.0729	0.4932	1.0729	1.0358
No log	44.0	264	1.2830	0.4540	1.2830	1.1327
No log	44.3333	266	1.4109	0.4304	1.4109	1.1878
No log	44.6667	268	1.3606	0.4431	1.3606	1.1665
No log	45.0	270	1.1910	0.4538	1.1910	1.0913
No log	45.3333	272	1.0497	0.4614	1.0497	1.0246
No log	45.6667	274	1.0641	0.4646	1.0641	1.0316
No log	46.0	276	1.1525	0.4652	1.1525	1.0736
No log	46.3333	278	1.1849	0.4588	1.1849	1.0885
No log	46.6667	280	1.2783	0.4439	1.2783	1.1306
No log	47.0	282	1.2992	0.4402	1.2992	1.1398
No log	47.3333	284	1.2056	0.4422	1.2056	1.0980
No log	47.6667	286	1.1211	0.4821	1.1211	1.0588
No log	48.0	288	1.2050	0.4631	1.2050	1.0977
No log	48.3333	290	1.3753	0.3996	1.3753	1.1727
No log	48.6667	292	1.4192	0.3549	1.4192	1.1913
No log	49.0	294	1.4119	0.3549	1.4119	1.1882
No log	49.3333	296	1.3158	0.4176	1.3158	1.1471
No log	49.6667	298	1.1409	0.4459	1.1409	1.0681
No log	50.0	300	1.0627	0.4131	1.0627	1.0309
No log	50.3333	302	1.0991	0.4587	1.0991	1.0484
No log	50.6667	304	1.2573	0.4428	1.2573	1.1213
No log	51.0	306	1.5665	0.3768	1.5665	1.2516
No log	51.3333	308	1.7116	0.3860	1.7116	1.3083
No log	51.6667	310	1.6314	0.3928	1.6314	1.2773
No log	52.0	312	1.4380	0.3792	1.4380	1.1992
No log	52.3333	314	1.2106	0.4860	1.2106	1.1003
No log	52.6667	316	1.1012	0.5234	1.1012	1.0494
No log	53.0	318	1.0726	0.4995	1.0726	1.0356
No log	53.3333	320	1.1201	0.5229	1.1201	1.0584
No log	53.6667	322	1.2013	0.4703	1.2013	1.0960
No log	54.0	324	1.2979	0.4235	1.2979	1.1392
No log	54.3333	326	1.3837	0.3526	1.3837	1.1763
No log	54.6667	328	1.3908	0.3652	1.3908	1.1793
No log	55.0	330	1.3817	0.3678	1.3817	1.1755
No log	55.3333	332	1.3380	0.4031	1.3380	1.1567
No log	55.6667	334	1.2873	0.4356	1.2873	1.1346
No log	56.0	336	1.2214	0.4568	1.2214	1.1052
No log	56.3333	338	1.2109	0.4576	1.2109	1.1004
No log	56.6667	340	1.1993	0.4720	1.1993	1.0951
No log	57.0	342	1.2684	0.4535	1.2684	1.1262
No log	57.3333	344	1.3405	0.4030	1.3405	1.1578
No log	57.6667	346	1.3619	0.3841	1.3619	1.1670
No log	58.0	348	1.2956	0.4225	1.2956	1.1382
No log	58.3333	350	1.1708	0.4532	1.1708	1.0820
No log	58.6667	352	1.1275	0.4452	1.1275	1.0618
No log	59.0	354	1.1578	0.4384	1.1578	1.0760
No log	59.3333	356	1.2580	0.4122	1.2580	1.1216
No log	59.6667	358	1.3219	0.4084	1.3219	1.1497
No log	60.0	360	1.3475	0.4131	1.3475	1.1608
No log	60.3333	362	1.3437	0.4232	1.3437	1.1592
No log	60.6667	364	1.3174	0.4282	1.3174	1.1478
No log	61.0	366	1.2752	0.4249	1.2752	1.1293
No log	61.3333	368	1.2101	0.4765	1.2101	1.1001
No log	61.6667	370	1.1923	0.4552	1.1923	1.0919
No log	62.0	372	1.2414	0.4454	1.2414	1.1142
No log	62.3333	374	1.2442	0.4572	1.2442	1.1155
No log	62.6667	376	1.2256	0.4715	1.2256	1.1071
No log	63.0	378	1.1583	0.4164	1.1583	1.0762
No log	63.3333	380	1.1316	0.4224	1.1316	1.0638
No log	63.6667	382	1.1563	0.4259	1.1563	1.0753
No log	64.0	384	1.1831	0.4410	1.1831	1.0877
No log	64.3333	386	1.2249	0.4431	1.2249	1.1067
No log	64.6667	388	1.2684	0.4388	1.2684	1.1262
No log	65.0	390	1.2763	0.4257	1.2763	1.1297
No log	65.3333	392	1.3269	0.4116	1.3269	1.1519
No log	65.6667	394	1.4042	0.3915	1.4042	1.1850
No log	66.0	396	1.4356	0.3734	1.4356	1.1982
No log	66.3333	398	1.4350	0.3734	1.4350	1.1979
No log	66.6667	400	1.3802	0.3776	1.3802	1.1748
No log	67.0	402	1.2820	0.4256	1.2820	1.1322
No log	67.3333	404	1.2262	0.4388	1.2262	1.1074
No log	67.6667	406	1.1520	0.5191	1.1520	1.0733
No log	68.0	408	1.1313	0.4824	1.1313	1.0636
No log	68.3333	410	1.1738	0.4841	1.1738	1.0834
No log	68.6667	412	1.2761	0.4138	1.2761	1.1296
No log	69.0	414	1.3849	0.3562	1.3849	1.1768
No log	69.3333	416	1.4189	0.3562	1.4189	1.1912
No log	69.6667	418	1.3654	0.3701	1.3654	1.1685
No log	70.0	420	1.2908	0.4139	1.2908	1.1361
No log	70.3333	422	1.2525	0.4233	1.2525	1.1191
No log	70.6667	424	1.2339	0.4278	1.2339	1.1108
No log	71.0	426	1.1828	0.4416	1.1828	1.0876
No log	71.3333	428	1.1385	0.4538	1.1385	1.0670
No log	71.6667	430	1.1489	0.4476	1.1489	1.0719
No log	72.0	432	1.2143	0.4382	1.2143	1.1020
No log	72.3333	434	1.3406	0.4013	1.3406	1.1578
No log	72.6667	436	1.4650	0.3602	1.4650	1.2104
No log	73.0	438	1.5052	0.3556	1.5052	1.2269
No log	73.3333	440	1.4615	0.3734	1.4615	1.2089
No log	73.6667	442	1.3637	0.4149	1.3637	1.1678
No log	74.0	444	1.2575	0.4282	1.2575	1.1214
No log	74.3333	446	1.1942	0.4513	1.1942	1.0928
No log	74.6667	448	1.1388	0.4728	1.1388	1.0672
No log	75.0	450	1.1433	0.4728	1.1433	1.0693
No log	75.3333	452	1.1844	0.4826	1.1844	1.0883
No log	75.6667	454	1.2160	0.4415	1.2160	1.1027
No log	76.0	456	1.2986	0.4301	1.2986	1.1396
No log	76.3333	458	1.3495	0.4130	1.3495	1.1617
No log	76.6667	460	1.3465	0.4262	1.3465	1.1604
No log	77.0	462	1.3790	0.3947	1.3790	1.1743
No log	77.3333	464	1.4127	0.3948	1.4127	1.1886
No log	77.6667	466	1.4400	0.3608	1.4400	1.2000
No log	78.0	468	1.4747	0.3608	1.4747	1.2144
No log	78.3333	470	1.4800	0.3720	1.4800	1.2165
No log	78.6667	472	1.4752	0.3917	1.4752	1.2146
No log	79.0	474	1.4339	0.3551	1.4339	1.1974
No log	79.3333	476	1.3707	0.3461	1.3707	1.1708
No log	79.6667	478	1.3008	0.3818	1.3008	1.1405
No log	80.0	480	1.2509	0.3960	1.2509	1.1185
No log	80.3333	482	1.2121	0.4598	1.2121	1.1010
No log	80.6667	484	1.2041	0.4796	1.2041	1.0973
No log	81.0	486	1.2146	0.4802	1.2146	1.1021
No log	81.3333	488	1.2276	0.4808	1.2276	1.1080
No log	81.6667	490	1.2318	0.4758	1.2318	1.1098
No log	82.0	492	1.2462	0.4415	1.2462	1.1163
No log	82.3333	494	1.2438	0.4321	1.2438	1.1153
No log	82.6667	496	1.2394	0.4415	1.2394	1.1133
No log	83.0	498	1.2219	0.4233	1.2219	1.1054
0.2306	83.3333	500	1.1804	0.4387	1.1804	1.0865
0.2306	83.6667	502	1.1517	0.4456	1.1517	1.0732
0.2306	84.0	504	1.1212	0.4636	1.1212	1.0588
0.2306	84.3333	506	1.0952	0.4597	1.0952	1.0465
0.2306	84.6667	508	1.1059	0.4636	1.1059	1.0516
0.2306	85.0	510	1.1369	0.4570	1.1369	1.0663
0.2306	85.3333	512	1.1952	0.4385	1.1952	1.0933
0.2306	85.6667	514	1.2324	0.4459	1.2324	1.1101
0.2306	86.0	516	1.2704	0.4123	1.2704	1.1271
0.2306	86.3333	518	1.2882	0.4123	1.2882	1.1350
0.2306	86.6667	520	1.3112	0.3941	1.3112	1.1451
0.2306	87.0	522	1.3373	0.4031	1.3373	1.1564
0.2306	87.3333	524	1.3248	0.4031	1.3248	1.1510

Framework versions

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