ArabicNewSplits6_FineTuningAraBERT_run2_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: 1.1386
• Qwk: 0.6022
• Mse: 1.1386
• Rmse: 1.0670

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	2.4082	0.0137	2.4082	1.5518
No log	0.1176	4	1.5267	0.2087	1.5267	1.2356
No log	0.1765	6	1.4284	0.1561	1.4284	1.1952
No log	0.2353	8	1.5042	0.1543	1.5042	1.2265
No log	0.2941	10	1.4282	0.1502	1.4282	1.1951
No log	0.3529	12	1.4061	0.1496	1.4061	1.1858
No log	0.4118	14	1.4265	0.1569	1.4265	1.1944
No log	0.4706	16	1.4242	0.1292	1.4242	1.1934
No log	0.5294	18	1.4583	0.1718	1.4583	1.2076
No log	0.5882	20	1.4602	0.2417	1.4602	1.2084
No log	0.6471	22	1.4220	0.2087	1.4220	1.1925
No log	0.7059	24	1.3436	0.1601	1.3436	1.1592
No log	0.7647	26	1.2805	0.2653	1.2805	1.1316
No log	0.8235	28	1.2598	0.3254	1.2598	1.1224
No log	0.8824	30	1.2121	0.3002	1.2121	1.1009
No log	0.9412	32	1.2386	0.3076	1.2386	1.1129
No log	1.0	34	1.3241	0.2867	1.3241	1.1507
No log	1.0588	36	1.3406	0.3734	1.3406	1.1578
No log	1.1176	38	1.2769	0.3101	1.2769	1.1300
No log	1.1765	40	1.1742	0.3199	1.1742	1.0836
No log	1.2353	42	1.1208	0.4144	1.1208	1.0587
No log	1.2941	44	1.1052	0.4045	1.1052	1.0513
No log	1.3529	46	1.0800	0.4724	1.0800	1.0392
No log	1.4118	48	1.0649	0.4352	1.0649	1.0319
No log	1.4706	50	1.1554	0.4681	1.1554	1.0749
No log	1.5294	52	1.2664	0.4516	1.2664	1.1254
No log	1.5882	54	1.2980	0.4463	1.2980	1.1393
No log	1.6471	56	1.2564	0.4610	1.2564	1.1209
No log	1.7059	58	1.2773	0.4637	1.2773	1.1302
No log	1.7647	60	1.2680	0.4637	1.2680	1.1260
No log	1.8235	62	1.2251	0.4610	1.2251	1.1068
No log	1.8824	64	1.2144	0.4701	1.2144	1.1020
No log	1.9412	66	1.0750	0.4772	1.0750	1.0368
No log	2.0	68	0.9633	0.5276	0.9633	0.9815
No log	2.0588	70	0.9482	0.5050	0.9482	0.9738
No log	2.1176	72	0.9558	0.5156	0.9558	0.9776
No log	2.1765	74	1.0899	0.4909	1.0899	1.0440
No log	2.2353	76	1.2871	0.4657	1.2871	1.1345
No log	2.2941	78	1.2839	0.4709	1.2839	1.1331
No log	2.3529	80	1.2378	0.4756	1.2378	1.1126
No log	2.4118	82	1.3922	0.4579	1.3922	1.1799
No log	2.4706	84	1.7948	0.3792	1.7948	1.3397
No log	2.5294	86	2.0900	0.3795	2.0900	1.4457
No log	2.5882	88	2.0156	0.3773	2.0156	1.4197
No log	2.6471	90	1.6931	0.4214	1.6931	1.3012
No log	2.7059	92	1.2058	0.4795	1.2058	1.0981
No log	2.7647	94	0.9995	0.5092	0.9995	0.9997
No log	2.8235	96	0.9513	0.4934	0.9513	0.9753
No log	2.8824	98	0.9682	0.4769	0.9682	0.9840
No log	2.9412	100	0.9761	0.4746	0.9761	0.9880
No log	3.0	102	1.0283	0.5216	1.0283	1.0140
No log	3.0588	104	1.1557	0.5281	1.1557	1.0750
No log	3.1176	106	1.3142	0.4919	1.3142	1.1464
No log	3.1765	108	1.2654	0.4715	1.2654	1.1249
No log	3.2353	110	1.1518	0.5530	1.1518	1.0732
No log	3.2941	112	1.0986	0.5428	1.0986	1.0481
No log	3.3529	114	1.2073	0.5161	1.2073	1.0988
No log	3.4118	116	1.4199	0.4746	1.4199	1.1916
No log	3.4706	118	1.6298	0.4818	1.6298	1.2766
No log	3.5294	120	1.7701	0.4837	1.7701	1.3304
No log	3.5882	122	1.7576	0.4937	1.7576	1.3257
No log	3.6471	124	1.5723	0.5030	1.5723	1.2539
No log	3.7059	126	1.5035	0.5001	1.5035	1.2262
No log	3.7647	128	1.4008	0.5388	1.4008	1.1836
No log	3.8235	130	1.3282	0.5233	1.3282	1.1525
No log	3.8824	132	1.3259	0.5233	1.3259	1.1515
No log	3.9412	134	1.2110	0.5373	1.2110	1.1005
No log	4.0	136	1.0928	0.5616	1.0928	1.0454
No log	4.0588	138	1.1813	0.5851	1.1813	1.0869
No log	4.1176	140	1.4262	0.5139	1.4262	1.1942
No log	4.1765	142	1.4548	0.5081	1.4548	1.2061
No log	4.2353	144	1.2314	0.5426	1.2314	1.1097
No log	4.2941	146	1.0339	0.5642	1.0339	1.0168
No log	4.3529	148	0.9523	0.6084	0.9523	0.9759
No log	4.4118	150	0.9785	0.5899	0.9785	0.9892
No log	4.4706	152	1.0848	0.5625	1.0848	1.0415
No log	4.5294	154	1.2963	0.5087	1.2963	1.1385
No log	4.5882	156	1.3580	0.5170	1.3580	1.1653
No log	4.6471	158	1.2892	0.5604	1.2892	1.1354
No log	4.7059	160	1.3007	0.5453	1.3007	1.1405
No log	4.7647	162	1.3379	0.5498	1.3379	1.1567
No log	4.8235	164	1.3989	0.5488	1.3989	1.1828
No log	4.8824	166	1.3227	0.5492	1.3227	1.1501
No log	4.9412	168	1.3111	0.5303	1.3111	1.1450
No log	5.0	170	1.2436	0.5767	1.2436	1.1152
No log	5.0588	172	1.1345	0.5821	1.1345	1.0651
No log	5.1176	174	1.1004	0.5821	1.1004	1.0490
No log	5.1765	176	1.1026	0.5956	1.1026	1.0501
No log	5.2353	178	0.9784	0.6204	0.9784	0.9892
No log	5.2941	180	0.8543	0.6284	0.8543	0.9243
No log	5.3529	182	0.8392	0.6475	0.8392	0.9161
No log	5.4118	184	0.9311	0.6280	0.9311	0.9650
No log	5.4706	186	1.1229	0.6132	1.1229	1.0597
No log	5.5294	188	1.3939	0.5539	1.3939	1.1806
No log	5.5882	190	1.4707	0.5508	1.4707	1.2127
No log	5.6471	192	1.3937	0.5635	1.3937	1.1805
No log	5.7059	194	1.1930	0.5737	1.1930	1.0923
No log	5.7647	196	0.9436	0.6207	0.9436	0.9714
No log	5.8235	198	0.8547	0.6274	0.8547	0.9245
No log	5.8824	200	0.8696	0.6341	0.8696	0.9325
No log	5.9412	202	0.9684	0.6179	0.9684	0.9841
No log	6.0	204	1.1713	0.5973	1.1713	1.0823
No log	6.0588	206	1.3164	0.5699	1.3164	1.1474
No log	6.1176	208	1.3399	0.5786	1.3399	1.1575
No log	6.1765	210	1.2807	0.5611	1.2807	1.1317
No log	6.2353	212	1.1840	0.5816	1.1840	1.0881
No log	6.2941	214	1.1113	0.6020	1.1113	1.0542
No log	6.3529	216	1.1144	0.5958	1.1144	1.0557
No log	6.4118	218	1.1905	0.5797	1.1905	1.0911
No log	6.4706	220	1.3243	0.5488	1.3243	1.1508
No log	6.5294	222	1.3824	0.5488	1.3824	1.1758
No log	6.5882	224	1.3412	0.5394	1.3412	1.1581
No log	6.6471	226	1.2635	0.5530	1.2635	1.1240
No log	6.7059	228	1.2071	0.5673	1.2071	1.0987
No log	6.7647	230	1.1690	0.5417	1.1690	1.0812
No log	6.8235	232	1.0885	0.5621	1.0885	1.0433
No log	6.8824	234	1.0152	0.5851	1.0152	1.0076
No log	6.9412	236	0.9884	0.5844	0.9884	0.9942
No log	7.0	238	0.9822	0.5971	0.9822	0.9910
No log	7.0588	240	0.9837	0.5969	0.9837	0.9918
No log	7.1176	242	0.9940	0.6150	0.9940	0.9970
No log	7.1765	244	1.0378	0.6126	1.0378	1.0187
No log	7.2353	246	1.0782	0.5702	1.0782	1.0384
No log	7.2941	248	1.1093	0.5769	1.1093	1.0532
No log	7.3529	250	1.1320	0.5790	1.1320	1.0640
No log	7.4118	252	1.1638	0.5683	1.1638	1.0788
No log	7.4706	254	1.1794	0.5726	1.1794	1.0860
No log	7.5294	256	1.2229	0.5644	1.2229	1.1059
No log	7.5882	258	1.2998	0.5554	1.2998	1.1401
No log	7.6471	260	1.3249	0.5679	1.3249	1.1511
No log	7.7059	262	1.2980	0.5767	1.2980	1.1393
No log	7.7647	264	1.2456	0.5635	1.2456	1.1161
No log	7.8235	266	1.1806	0.5767	1.1806	1.0865
No log	7.8824	268	1.1240	0.6032	1.1240	1.0602
No log	7.9412	270	1.0822	0.6119	1.0822	1.0403
No log	8.0	272	1.0718	0.6135	1.0718	1.0353
No log	8.0588	274	1.0575	0.6095	1.0575	1.0283
No log	8.1176	276	1.0755	0.6103	1.0755	1.0371
No log	8.1765	278	1.0740	0.6103	1.0740	1.0364
No log	8.2353	280	1.0682	0.6103	1.0682	1.0335
No log	8.2941	282	1.0506	0.6095	1.0506	1.0250
No log	8.3529	284	1.0649	0.6103	1.0649	1.0320
No log	8.4118	286	1.0734	0.6103	1.0734	1.0361
No log	8.4706	288	1.0832	0.6103	1.0832	1.0408
No log	8.5294	290	1.1030	0.5988	1.1030	1.0503
No log	8.5882	292	1.1128	0.5988	1.1128	1.0549
No log	8.6471	294	1.1078	0.6074	1.1078	1.0525
No log	8.7059	296	1.1114	0.6103	1.1114	1.0542
No log	8.7647	298	1.1360	0.6165	1.1360	1.0658
No log	8.8235	300	1.1666	0.6085	1.1666	1.0801
No log	8.8824	302	1.1838	0.6051	1.1838	1.0880
No log	8.9412	304	1.2165	0.5824	1.2165	1.1029
No log	9.0	306	1.2504	0.5776	1.2504	1.1182
No log	9.0588	308	1.2643	0.5766	1.2643	1.1244
No log	9.1176	310	1.2566	0.5766	1.2566	1.1210
No log	9.1765	312	1.2300	0.5776	1.2300	1.1091
No log	9.2353	314	1.1944	0.5903	1.1944	1.0929
No log	9.2941	316	1.1582	0.6170	1.1582	1.0762
No log	9.3529	318	1.1459	0.6109	1.1459	1.0705
No log	9.4118	320	1.1369	0.6022	1.1369	1.0663
No log	9.4706	322	1.1283	0.6022	1.1283	1.0622
No log	9.5294	324	1.1194	0.6022	1.1194	1.0580
No log	9.5882	326	1.1235	0.6022	1.1235	1.0599
No log	9.6471	328	1.1280	0.6022	1.1280	1.0621
No log	9.7059	330	1.1292	0.6022	1.1292	1.0626
No log	9.7647	332	1.1305	0.6022	1.1305	1.0632
No log	9.8235	334	1.1312	0.6022	1.1312	1.0636
No log	9.8824	336	1.1337	0.6022	1.1337	1.0647
No log	9.9412	338	1.1368	0.6022	1.1368	1.0662
No log	10.0	340	1.1386	0.6022	1.1386	1.0670

Framework versions

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