ArabicNewSplits6_FineTuningAraBERT_run3_AugV5_k9_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: 1.1207
• Qwk: 0.5339
• Mse: 1.1207
• Rmse: 1.0586

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	2.5324	-0.0377	2.5324	1.5913
No log	0.1176	4	1.9494	0.0212	1.9494	1.3962
No log	0.1765	6	2.0501	-0.1052	2.0501	1.4318
No log	0.2353	8	1.9755	0.0529	1.9755	1.4055
No log	0.2941	10	1.8354	0.1089	1.8354	1.3548
No log	0.3529	12	1.8089	0.1546	1.8089	1.3449
No log	0.4118	14	1.7597	0.1561	1.7597	1.3265
No log	0.4706	16	1.7546	0.1238	1.7546	1.3246
No log	0.5294	18	1.7000	0.0678	1.7000	1.3038
No log	0.5882	20	1.5127	0.0922	1.5127	1.2299
No log	0.6471	22	1.4466	0.1544	1.4466	1.2028
No log	0.7059	24	1.6073	0.3157	1.6073	1.2678
No log	0.7647	26	1.8577	0.2902	1.8577	1.3630
No log	0.8235	28	1.9413	0.2587	1.9413	1.3933
No log	0.8824	30	1.8418	0.2991	1.8418	1.3571
No log	0.9412	32	1.6204	0.3248	1.6204	1.2729
No log	1.0	34	1.4493	0.2236	1.4493	1.2039
No log	1.0588	36	1.3746	0.1686	1.3746	1.1724
No log	1.1176	38	1.2904	0.1857	1.2904	1.1360
No log	1.1765	40	1.2361	0.2119	1.2361	1.1118
No log	1.2353	42	1.2231	0.1974	1.2231	1.1060
No log	1.2941	44	1.2623	0.2826	1.2623	1.1235
No log	1.3529	46	1.3154	0.2628	1.3154	1.1469
No log	1.4118	48	1.4391	0.3382	1.4391	1.1996
No log	1.4706	50	1.5391	0.3743	1.5391	1.2406
No log	1.5294	52	1.4932	0.3603	1.4932	1.2220
No log	1.5882	54	1.4293	0.3555	1.4293	1.1955
No log	1.6471	56	1.4774	0.4035	1.4774	1.2155
No log	1.7059	58	1.4332	0.3161	1.4332	1.1972
No log	1.7647	60	1.3558	0.3170	1.3558	1.1644
No log	1.8235	62	1.3394	0.3022	1.3394	1.1573
No log	1.8824	64	1.3284	0.3022	1.3284	1.1526
No log	1.9412	66	1.2377	0.4084	1.2377	1.1125
No log	2.0	68	1.2257	0.4244	1.2257	1.1071
No log	2.0588	70	1.2714	0.4049	1.2714	1.1275
No log	2.1176	72	1.3422	0.3785	1.3422	1.1585
No log	2.1765	74	1.5090	0.3910	1.5090	1.2284
No log	2.2353	76	1.6321	0.3557	1.6321	1.2775
No log	2.2941	78	1.8076	0.3407	1.8076	1.3445
No log	2.3529	80	1.7488	0.3420	1.7488	1.3224
No log	2.4118	82	1.5469	0.3678	1.5469	1.2438
No log	2.4706	84	1.3746	0.4283	1.3746	1.1724
No log	2.5294	86	1.3673	0.4872	1.3673	1.1693
No log	2.5882	88	1.5827	0.3732	1.5827	1.2580
No log	2.6471	90	1.6183	0.3784	1.6183	1.2721
No log	2.7059	92	1.4302	0.4102	1.4302	1.1959
No log	2.7647	94	1.2543	0.4678	1.2543	1.1199
No log	2.8235	96	1.1578	0.4017	1.1578	1.0760
No log	2.8824	98	1.1607	0.4333	1.1607	1.0773
No log	2.9412	100	1.2479	0.4453	1.2479	1.1171
No log	3.0	102	1.3809	0.4225	1.3809	1.1751
No log	3.0588	104	1.4818	0.3865	1.4818	1.2173
No log	3.1176	106	1.6004	0.3494	1.6004	1.2651
No log	3.1765	108	1.5611	0.4038	1.5611	1.2494
No log	3.2353	110	1.4375	0.4629	1.4375	1.1990
No log	3.2941	112	1.3643	0.4685	1.3643	1.1680
No log	3.3529	114	1.3882	0.4685	1.3882	1.1782
No log	3.4118	116	1.4522	0.4665	1.4522	1.2051
No log	3.4706	118	1.4640	0.4390	1.4640	1.2100
No log	3.5294	120	1.3280	0.4644	1.3280	1.1524
No log	3.5882	122	1.1428	0.4822	1.1428	1.0690
No log	3.6471	124	1.0485	0.5246	1.0485	1.0240
No log	3.7059	126	1.0354	0.5234	1.0354	1.0175
No log	3.7647	128	1.0752	0.5493	1.0752	1.0369
No log	3.8235	130	1.2238	0.5278	1.2238	1.1063
No log	3.8824	132	1.3132	0.4959	1.3132	1.1459
No log	3.9412	134	1.2616	0.4750	1.2616	1.1232
No log	4.0	136	1.1451	0.5010	1.1451	1.0701
No log	4.0588	138	1.0721	0.4679	1.0721	1.0354
No log	4.1176	140	1.0527	0.4645	1.0527	1.0260
No log	4.1765	142	1.0750	0.4645	1.0750	1.0368
No log	4.2353	144	1.1967	0.5077	1.1967	1.0939
No log	4.2941	146	1.4230	0.4068	1.4230	1.1929
No log	4.3529	148	1.6445	0.4069	1.6445	1.2824
No log	4.4118	150	1.7098	0.4042	1.7098	1.3076
No log	4.4706	152	1.6232	0.4141	1.6232	1.2741
No log	4.5294	154	1.4846	0.4213	1.4846	1.2184
No log	4.5882	156	1.3306	0.4731	1.3306	1.1535
No log	4.6471	158	1.1787	0.5037	1.1787	1.0857
No log	4.7059	160	1.1318	0.5080	1.1318	1.0639
No log	4.7647	162	1.1961	0.5224	1.1961	1.0937
No log	4.8235	164	1.2380	0.5253	1.2380	1.1127
No log	4.8824	166	1.3228	0.5008	1.3228	1.1501
No log	4.9412	168	1.2701	0.5264	1.2701	1.1270
No log	5.0	170	1.1804	0.5468	1.1804	1.0865
No log	5.0588	172	1.0961	0.5529	1.0961	1.0469
No log	5.1176	174	1.0145	0.5682	1.0145	1.0072
No log	5.1765	176	0.9681	0.5718	0.9681	0.9839
No log	5.2353	178	0.9775	0.5618	0.9775	0.9887
No log	5.2941	180	1.0045	0.5618	1.0045	1.0022
No log	5.3529	182	1.0626	0.5527	1.0626	1.0308
No log	5.4118	184	1.0860	0.5433	1.0860	1.0421
No log	5.4706	186	1.1696	0.5454	1.1696	1.0815
No log	5.5294	188	1.1865	0.5300	1.1865	1.0893
No log	5.5882	190	1.1891	0.5283	1.1891	1.0905
No log	5.6471	192	1.1763	0.5245	1.1763	1.0846
No log	5.7059	194	1.1630	0.5300	1.1630	1.0784
No log	5.7647	196	1.0810	0.5513	1.0810	1.0397
No log	5.8235	198	0.9947	0.5618	0.9947	0.9973
No log	5.8824	200	0.9891	0.5541	0.9891	0.9945
No log	5.9412	202	1.0562	0.5622	1.0562	1.0277
No log	6.0	204	1.1849	0.5099	1.1849	1.0885
No log	6.0588	206	1.2798	0.5301	1.2798	1.1313
No log	6.1176	208	1.3106	0.5321	1.3106	1.1448
No log	6.1765	210	1.2974	0.5244	1.2974	1.1390
No log	6.2353	212	1.1917	0.5199	1.1917	1.0917
No log	6.2941	214	1.0841	0.5448	1.0841	1.0412
No log	6.3529	216	1.0236	0.5371	1.0236	1.0117
No log	6.4118	218	1.0325	0.5450	1.0325	1.0161
No log	6.4706	220	1.0770	0.5464	1.0770	1.0378
No log	6.5294	222	1.1302	0.5039	1.1302	1.0631
No log	6.5882	224	1.2193	0.5012	1.2193	1.1042
No log	6.6471	226	1.2361	0.5012	1.2361	1.1118
No log	6.7059	228	1.2360	0.5101	1.2360	1.1117
No log	6.7647	230	1.1913	0.5199	1.1913	1.0915
No log	6.8235	232	1.1309	0.5493	1.1309	1.0634
No log	6.8824	234	1.0975	0.5647	1.0975	1.0476
No log	6.9412	236	1.1150	0.5399	1.1150	1.0559
No log	7.0	238	1.1118	0.5397	1.1118	1.0544
No log	7.0588	240	1.1307	0.5357	1.1307	1.0633
No log	7.1176	242	1.1229	0.5348	1.1229	1.0597
No log	7.1765	244	1.0891	0.5608	1.0891	1.0436
No log	7.2353	246	1.0462	0.5810	1.0462	1.0228
No log	7.2941	248	1.0530	0.5708	1.0530	1.0261
No log	7.3529	250	1.0738	0.5696	1.0738	1.0362
No log	7.4118	252	1.0668	0.5510	1.0668	1.0329
No log	7.4706	254	1.0857	0.5510	1.0857	1.0419
No log	7.5294	256	1.0968	0.5548	1.0968	1.0473
No log	7.5882	258	1.1340	0.5537	1.1340	1.0649
No log	7.6471	260	1.1808	0.5202	1.1808	1.0867
No log	7.7059	262	1.2269	0.4971	1.2269	1.1076
No log	7.7647	264	1.2355	0.4971	1.2355	1.1115
No log	7.8235	266	1.2097	0.5143	1.2097	1.0999
No log	7.8824	268	1.1571	0.5251	1.1571	1.0757
No log	7.9412	270	1.1147	0.5487	1.1147	1.0558
No log	8.0	272	1.0990	0.5623	1.0990	1.0483
No log	8.0588	274	1.0755	0.5673	1.0755	1.0371
No log	8.1176	276	1.1011	0.5673	1.1011	1.0494
No log	8.1765	278	1.1209	0.5575	1.1209	1.0587
No log	8.2353	280	1.1332	0.5403	1.1332	1.0645
No log	8.2941	282	1.1358	0.5413	1.1358	1.0657
No log	8.3529	284	1.1524	0.5413	1.1524	1.0735
No log	8.4118	286	1.1488	0.5442	1.1488	1.0718
No log	8.4706	288	1.1377	0.5442	1.1377	1.0666
No log	8.5294	290	1.1264	0.5413	1.1264	1.0613
No log	8.5882	292	1.1346	0.5272	1.1346	1.0652
No log	8.6471	294	1.1526	0.5339	1.1526	1.0736
No log	8.7059	296	1.1586	0.5339	1.1586	1.0764
No log	8.7647	298	1.1495	0.5339	1.1495	1.0722
No log	8.8235	300	1.1289	0.5339	1.1289	1.0625
No log	8.8824	302	1.1171	0.5339	1.1171	1.0569
No log	8.9412	304	1.1272	0.5528	1.1272	1.0617
No log	9.0	306	1.1395	0.5394	1.1395	1.0675
No log	9.0588	308	1.1581	0.5394	1.1581	1.0761
No log	9.1176	310	1.1610	0.5394	1.1610	1.0775
No log	9.1765	312	1.1460	0.5394	1.1460	1.0705
No log	9.2353	314	1.1358	0.5394	1.1358	1.0657
No log	9.2941	316	1.1337	0.5394	1.1337	1.0647
No log	9.3529	318	1.1228	0.5394	1.1228	1.0596
No log	9.4118	320	1.1115	0.5528	1.1115	1.0543
No log	9.4706	322	1.1032	0.5397	1.1032	1.0503
No log	9.5294	324	1.0944	0.5303	1.0944	1.0461
No log	9.5882	326	1.0915	0.5303	1.0915	1.0448
No log	9.6471	328	1.0942	0.5303	1.0942	1.0461
No log	9.7059	330	1.1002	0.5303	1.1002	1.0489
No log	9.7647	332	1.1044	0.5303	1.1044	1.0509
No log	9.8235	334	1.1094	0.5303	1.1094	1.0533
No log	9.8824	336	1.1156	0.5339	1.1156	1.0562
No log	9.9412	338	1.1194	0.5339	1.1194	1.0580
No log	10.0	340	1.1207	0.5339	1.1207	1.0586

Framework versions

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