ArabicNewSplits2_FineTuningAraBERT_run1_AugV4_k5_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: 1.1718
• Qwk: 0.5168
• Mse: 1.1718
• Rmse: 1.0825

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	0.0444	2	4.6634	-0.0151	4.6634	2.1595
No log	0.0889	4	2.6540	0.0706	2.6540	1.6291
No log	0.1333	6	1.6532	0.1117	1.6532	1.2858
No log	0.1778	8	1.1341	0.2996	1.1341	1.0649
No log	0.2222	10	1.1982	0.2410	1.1982	1.0946
No log	0.2667	12	1.4242	0.1376	1.4242	1.1934
No log	0.3111	14	1.8299	0.2380	1.8299	1.3528
No log	0.3556	16	2.1219	0.2174	2.1219	1.4567
No log	0.4	18	2.1581	0.2053	2.1581	1.4691
No log	0.4444	20	2.1251	0.2135	2.1251	1.4578
No log	0.4889	22	2.2780	0.1725	2.2780	1.5093
No log	0.5333	24	1.7867	0.0520	1.7867	1.3367
No log	0.5778	26	1.6330	0.0388	1.6330	1.2779
No log	0.6222	28	1.6726	0.0601	1.6726	1.2933
No log	0.6667	30	2.1999	0.1725	2.1999	1.4832
No log	0.7111	32	2.3598	0.1293	2.3598	1.5362
No log	0.7556	34	2.4522	0.1056	2.4522	1.5660
No log	0.8	36	2.4139	0.1635	2.4139	1.5537
No log	0.8444	38	1.9797	0.2518	1.9797	1.4070
No log	0.8889	40	2.2642	0.1635	2.2642	1.5047
No log	0.9333	42	2.2425	0.1379	2.2425	1.4975
No log	0.9778	44	2.1548	0.1328	2.1548	1.4679
No log	1.0222	46	1.8792	0.2429	1.8792	1.3708
No log	1.0667	48	1.7204	0.2990	1.7204	1.3117
No log	1.1111	50	1.6395	0.3379	1.6395	1.2804
No log	1.1556	52	1.3807	0.4812	1.3807	1.1750
No log	1.2	54	1.2376	0.5036	1.2376	1.1125
No log	1.2444	56	1.2843	0.5132	1.2843	1.1333
No log	1.2889	58	1.4224	0.4205	1.4224	1.1927
No log	1.3333	60	1.1378	0.4665	1.1378	1.0667
No log	1.3778	62	1.0731	0.4919	1.0731	1.0359
No log	1.4222	64	1.2402	0.3938	1.2402	1.1136
No log	1.4667	66	1.1288	0.5263	1.1288	1.0625
No log	1.5111	68	1.0728	0.5263	1.0728	1.0358
No log	1.5556	70	0.9952	0.5664	0.9952	0.9976
No log	1.6	72	1.0265	0.5535	1.0265	1.0132
No log	1.6444	74	1.1251	0.4860	1.1251	1.0607
No log	1.6889	76	1.3597	0.4052	1.3597	1.1661
No log	1.7333	78	1.6356	0.3386	1.6356	1.2789
No log	1.7778	80	1.6027	0.3386	1.6027	1.2660
No log	1.8222	82	1.3396	0.4375	1.3396	1.1574
No log	1.8667	84	1.1917	0.3983	1.1917	1.0916
No log	1.9111	86	1.1166	0.4898	1.1166	1.0567
No log	1.9556	88	1.2470	0.3841	1.2470	1.1167
No log	2.0	90	1.4543	0.3192	1.4543	1.2059
No log	2.0444	92	1.8470	0.3116	1.8470	1.3590
No log	2.0889	94	1.9633	0.3161	1.9633	1.4012
No log	2.1333	96	1.7282	0.3116	1.7282	1.3146
No log	2.1778	98	1.6606	0.3461	1.6606	1.2886
No log	2.2222	100	1.5360	0.3894	1.5360	1.2394
No log	2.2667	102	1.3902	0.4496	1.3902	1.1791
No log	2.3111	104	1.2781	0.5406	1.2781	1.1305
No log	2.3556	106	1.4536	0.4496	1.4536	1.2057
No log	2.4	108	1.7269	0.3304	1.7269	1.3141
No log	2.4444	110	1.5967	0.3017	1.5967	1.2636
No log	2.4889	112	1.3034	0.4733	1.3034	1.1416
No log	2.5333	114	1.2286	0.5322	1.2286	1.1084
No log	2.5778	116	1.1541	0.5341	1.1541	1.0743
No log	2.6222	118	1.0442	0.5512	1.0442	1.0219
No log	2.6667	120	0.8952	0.5451	0.8952	0.9461
No log	2.7111	122	0.8306	0.6082	0.8306	0.9114
No log	2.7556	124	0.9058	0.5972	0.9058	0.9517
No log	2.8	126	1.0301	0.5998	1.0301	1.0149
No log	2.8444	128	0.9010	0.5972	0.9010	0.9492
No log	2.8889	130	0.9161	0.5972	0.9161	0.9571
No log	2.9333	132	0.8507	0.6082	0.8507	0.9223
No log	2.9778	134	0.8730	0.5960	0.8730	0.9343
No log	3.0222	136	1.0175	0.6043	1.0175	1.0087
No log	3.0667	138	1.0109	0.6149	1.0109	1.0054
No log	3.1111	140	1.0001	0.6149	1.0001	1.0000
No log	3.1556	142	1.1149	0.6165	1.1149	1.0559
No log	3.2	144	1.1728	0.5542	1.1728	1.0830
No log	3.2444	146	1.3294	0.5068	1.3294	1.1530
No log	3.2889	148	1.3238	0.5263	1.3238	1.1506
No log	3.3333	150	1.1507	0.5612	1.1507	1.0727
No log	3.3778	152	0.9880	0.6233	0.9880	0.9940
No log	3.4222	154	0.9535	0.6011	0.9535	0.9765
No log	3.4667	156	0.9993	0.5964	0.9993	0.9996
No log	3.5111	158	1.1096	0.5809	1.1096	1.0534
No log	3.5556	160	1.1466	0.5749	1.1466	1.0708
No log	3.6	162	1.1149	0.5918	1.1149	1.0559
No log	3.6444	164	1.0304	0.5862	1.0304	1.0151
No log	3.6889	166	0.8727	0.5804	0.8727	0.9342
No log	3.7333	168	0.8424	0.6413	0.8424	0.9178
No log	3.7778	170	0.9186	0.5553	0.9186	0.9584
No log	3.8222	172	1.3088	0.5135	1.3088	1.1440
No log	3.8667	174	1.6291	0.4155	1.6291	1.2764
No log	3.9111	176	1.5556	0.4038	1.5556	1.2472
No log	3.9556	178	1.2108	0.4625	1.2108	1.1004
No log	4.0	180	1.0970	0.4886	1.0970	1.0474
No log	4.0444	182	1.0746	0.4637	1.0746	1.0366
No log	4.0889	184	1.0431	0.4522	1.0431	1.0213
No log	4.1333	186	1.0485	0.4813	1.0485	1.0240
No log	4.1778	188	1.1848	0.4876	1.1848	1.0885
No log	4.2222	190	1.3930	0.4723	1.3930	1.1803
No log	4.2667	192	1.3458	0.5491	1.3458	1.1601
No log	4.3111	194	1.1612	0.6148	1.1612	1.0776
No log	4.3556	196	0.8998	0.5837	0.8998	0.9486
No log	4.4	198	0.8561	0.5938	0.8561	0.9252
No log	4.4444	200	0.9111	0.5837	0.9111	0.9545
No log	4.4889	202	1.1652	0.6107	1.1652	1.0794
No log	4.5333	204	1.4179	0.5185	1.4179	1.1908
No log	4.5778	206	1.4035	0.5	1.4035	1.1847
No log	4.6222	208	1.1720	0.5960	1.1720	1.0826
No log	4.6667	210	1.0081	0.5964	1.0081	1.0041
No log	4.7111	212	0.9855	0.5512	0.9855	0.9927
No log	4.7556	214	1.0926	0.5361	1.0926	1.0453
No log	4.8	216	1.1174	0.5233	1.1174	1.0571
No log	4.8444	218	1.2009	0.5075	1.2009	1.0958
No log	4.8889	220	1.1894	0.5075	1.1894	1.0906
No log	4.9333	222	1.2151	0.5061	1.2151	1.1023
No log	4.9778	224	1.1027	0.5568	1.1027	1.0501
No log	5.0222	226	1.0241	0.5615	1.0241	1.0120
No log	5.0667	228	1.0326	0.5837	1.0326	1.0162
No log	5.1111	230	1.1198	0.5189	1.1198	1.0582
No log	5.1556	232	1.2902	0.4830	1.2902	1.1359
No log	5.2	234	1.5070	0.4727	1.5070	1.2276
No log	5.2444	236	1.4707	0.4727	1.4707	1.2127
No log	5.2889	238	1.2749	0.5031	1.2749	1.1291
No log	5.3333	240	1.1912	0.5190	1.1912	1.0914
No log	5.3778	242	1.0409	0.5800	1.0409	1.0202
No log	5.4222	244	0.8852	0.6047	0.8852	0.9408
No log	5.4667	246	0.8798	0.6119	0.8798	0.9380
No log	5.5111	248	0.9813	0.5800	0.9813	0.9906
No log	5.5556	250	1.2339	0.4614	1.2339	1.1108
No log	5.6	252	1.3624	0.3916	1.3624	1.1672
No log	5.6444	254	1.4652	0.3916	1.4652	1.2105
No log	5.6889	256	1.5255	0.3916	1.5255	1.2351
No log	5.7333	258	1.4062	0.3916	1.4062	1.1858
No log	5.7778	260	1.2545	0.4375	1.2545	1.1201
No log	5.8222	262	1.2273	0.5322	1.2273	1.1079
No log	5.8667	264	1.2702	0.5175	1.2702	1.1270
No log	5.9111	266	1.2659	0.5056	1.2659	1.1251
No log	5.9556	268	1.0855	0.5918	1.0855	1.0419
No log	6.0	270	0.9996	0.5964	0.9996	0.9998
No log	6.0444	272	1.0659	0.5691	1.0659	1.0324
No log	6.0889	274	1.2118	0.5509	1.2118	1.1008
No log	6.1333	276	1.2394	0.5509	1.2394	1.1133
No log	6.1778	278	1.2002	0.5527	1.2002	1.0956
No log	6.2222	280	1.0940	0.5586	1.0940	1.0460
No log	6.2667	282	0.9871	0.5964	0.9871	0.9935
No log	6.3111	284	1.0173	0.5675	1.0173	1.0086
No log	6.3556	286	1.0525	0.5468	1.0525	1.0259
No log	6.4	288	1.0290	0.5927	1.0290	1.0144
No log	6.4444	290	1.0728	0.5909	1.0728	1.0357
No log	6.4889	292	1.1396	0.5196	1.1396	1.0675
No log	6.5333	294	1.2513	0.4968	1.2513	1.1186
No log	6.5778	296	1.2701	0.4968	1.2701	1.1270
No log	6.6222	298	1.2272	0.4968	1.2272	1.1078
No log	6.6667	300	1.1351	0.5312	1.1351	1.0654
No log	6.7111	302	0.9566	0.6481	0.9566	0.9781
No log	6.7556	304	0.8613	0.5835	0.8613	0.9281
No log	6.8	306	0.8578	0.5835	0.8578	0.9262
No log	6.8444	308	0.9374	0.6286	0.9374	0.9682
No log	6.8889	310	1.0526	0.5568	1.0526	1.0260
No log	6.9333	312	1.1090	0.5085	1.1090	1.0531
No log	6.9778	314	1.1131	0.5085	1.1131	1.0550
No log	7.0222	316	1.0916	0.5206	1.0916	1.0448
No log	7.0667	318	1.1362	0.55	1.1362	1.0659
No log	7.1111	320	1.1662	0.5085	1.1662	1.0799
No log	7.1556	322	1.1855	0.5085	1.1855	1.0888
No log	7.2	324	1.1307	0.5426	1.1307	1.0633
No log	7.2444	326	1.1449	0.5206	1.1449	1.0700
No log	7.2889	328	1.1671	0.5081	1.1671	1.0803
No log	7.3333	330	1.1342	0.5667	1.1342	1.0650
No log	7.3778	332	1.0875	0.6197	1.0875	1.0429
No log	7.4222	334	1.0825	0.5788	1.0825	1.0405
No log	7.4667	336	1.0862	0.5488	1.0862	1.0422
No log	7.5111	338	1.1311	0.5233	1.1311	1.0635
No log	7.5556	340	1.2042	0.5104	1.2042	1.0973
No log	7.6	342	1.2497	0.5104	1.2497	1.1179
No log	7.6444	344	1.2366	0.5422	1.2366	1.1120
No log	7.6889	346	1.2372	0.5085	1.2372	1.1123
No log	7.7333	348	1.1853	0.5521	1.1853	1.0887
No log	7.7778	350	1.1438	0.5843	1.1438	1.0695
No log	7.8222	352	1.1110	0.6388	1.1110	1.0540
No log	7.8667	354	1.0802	0.6152	1.0802	1.0393
No log	7.9111	356	1.1002	0.5949	1.1002	1.0489
No log	7.9556	358	1.1699	0.5304	1.1699	1.0816
No log	8.0	360	1.2142	0.4989	1.2142	1.1019
No log	8.0444	362	1.2814	0.4956	1.2814	1.1320
No log	8.0889	364	1.3249	0.4643	1.3249	1.1511
No log	8.1333	366	1.3192	0.4752	1.3192	1.1485
No log	8.1778	368	1.2588	0.4958	1.2588	1.1220
No log	8.2222	370	1.2288	0.5168	1.2288	1.1085
No log	8.2667	372	1.2114	0.5273	1.2114	1.1007
No log	8.3111	374	1.1484	0.5666	1.1484	1.0717
No log	8.3556	376	1.1253	0.5666	1.1253	1.0608
No log	8.4	378	1.1238	0.5666	1.1238	1.0601
No log	8.4444	380	1.1187	0.5666	1.1187	1.0577
No log	8.4889	382	1.1260	0.5669	1.1260	1.0611
No log	8.5333	384	1.1756	0.5481	1.1756	1.0843
No log	8.5778	386	1.1778	0.53	1.1778	1.0853
No log	8.6222	388	1.1857	0.53	1.1857	1.0889
No log	8.6667	390	1.1432	0.6026	1.1432	1.0692
No log	8.7111	392	1.1329	0.6026	1.1329	1.0644
No log	8.7556	394	1.1379	0.6026	1.1379	1.0667
No log	8.8	396	1.1243	0.6026	1.1243	1.0603
No log	8.8444	398	1.1311	0.6026	1.1311	1.0635
No log	8.8889	400	1.1343	0.6026	1.1343	1.0651
No log	8.9333	402	1.1212	0.6026	1.1212	1.0589
No log	8.9778	404	1.1261	0.5835	1.1261	1.0612
No log	9.0222	406	1.1222	0.5835	1.1222	1.0593
No log	9.0667	408	1.1327	0.5835	1.1327	1.0643
No log	9.1111	410	1.1291	0.5835	1.1291	1.0626
No log	9.1556	412	1.1181	0.5835	1.1181	1.0574
No log	9.2	414	1.1262	0.5610	1.1262	1.0612
No log	9.2444	416	1.1437	0.5196	1.1437	1.0694
No log	9.2889	418	1.1712	0.4652	1.1712	1.0822
No log	9.3333	420	1.1798	0.4752	1.1798	1.0862
No log	9.3778	422	1.1757	0.4752	1.1757	1.0843
No log	9.4222	424	1.1536	0.5196	1.1536	1.0741
No log	9.4667	426	1.1421	0.5196	1.1421	1.0687
No log	9.5111	428	1.1236	0.5196	1.1236	1.0600
No log	9.5556	430	1.1032	0.5828	1.1032	1.0503
No log	9.6	432	1.0965	0.5828	1.0965	1.0471
No log	9.6444	434	1.0946	0.5828	1.0946	1.0462
No log	9.6889	436	1.1029	0.5828	1.1029	1.0502
No log	9.7333	438	1.1134	0.5211	1.1134	1.0552
No log	9.7778	440	1.1273	0.5196	1.1273	1.0618
No log	9.8222	442	1.1436	0.5273	1.1436	1.0694
No log	9.8667	444	1.1562	0.5273	1.1562	1.0753
No log	9.9111	446	1.1651	0.5273	1.1651	1.0794
No log	9.9556	448	1.1706	0.5168	1.1706	1.0820
No log	10.0	450	1.1718	0.5168	1.1718	1.0825

Framework versions

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