ArabicNewSplits5_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: 0.9997
• Qwk: 0.6161
• Mse: 0.9997
• Rmse: 0.9998

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	0.0455	2	2.2207	0.0285	2.2207	1.4902
No log	0.0909	4	1.6256	0.2001	1.6256	1.2750
No log	0.1364	6	1.3812	0.2813	1.3812	1.1753
No log	0.1818	8	1.5709	0.0325	1.5709	1.2533
No log	0.2273	10	1.5805	0.1127	1.5805	1.2572
No log	0.2727	12	1.6514	0.2076	1.6514	1.2851
No log	0.3182	14	1.6253	0.1734	1.6253	1.2749
No log	0.3636	16	1.5356	0.0836	1.5356	1.2392
No log	0.4091	18	1.4754	0.1650	1.4754	1.2147
No log	0.4545	20	1.3763	0.2014	1.3763	1.1732
No log	0.5	22	1.3161	0.2389	1.3161	1.1472
No log	0.5455	24	1.3203	0.1762	1.3203	1.1491
No log	0.5909	26	1.3507	0.1627	1.3507	1.1622
No log	0.6364	28	1.3137	0.1220	1.3137	1.1462
No log	0.6818	30	1.2413	0.1347	1.2413	1.1141
No log	0.7273	32	1.1722	0.1715	1.1722	1.0827
No log	0.7727	34	1.1476	0.1715	1.1476	1.0713
No log	0.8182	36	1.1211	0.2505	1.1211	1.0588
No log	0.8636	38	1.1174	0.3286	1.1174	1.0571
No log	0.9091	40	1.0967	0.3930	1.0967	1.0472
No log	0.9545	42	1.0682	0.4825	1.0682	1.0335
No log	1.0	44	1.1898	0.3549	1.1898	1.0908
No log	1.0455	46	1.1862	0.3358	1.1862	1.0891
No log	1.0909	48	1.0924	0.4406	1.0924	1.0452
No log	1.1364	50	1.1540	0.3763	1.1540	1.0742
No log	1.1818	52	1.2869	0.4290	1.2869	1.1344
No log	1.2273	54	1.4728	0.3644	1.4728	1.2136
No log	1.2727	56	1.3616	0.4437	1.3616	1.1669
No log	1.3182	58	1.1014	0.3710	1.1014	1.0495
No log	1.3636	60	1.0926	0.4346	1.0926	1.0453
No log	1.4091	62	1.0854	0.4393	1.0854	1.0418
No log	1.4545	64	1.0879	0.3881	1.0879	1.0430
No log	1.5	66	1.1785	0.4351	1.1785	1.0856
No log	1.5455	68	1.1844	0.4632	1.1844	1.0883
No log	1.5909	70	1.2100	0.4638	1.2100	1.1000
No log	1.6364	72	1.1305	0.4987	1.1305	1.0632
No log	1.6818	74	1.0123	0.5030	1.0123	1.0061
No log	1.7273	76	1.1010	0.4146	1.1010	1.0493
No log	1.7727	78	1.1495	0.3752	1.1495	1.0721
No log	1.8182	80	1.0779	0.3848	1.0779	1.0382
No log	1.8636	82	1.0085	0.4817	1.0085	1.0042
No log	1.9091	84	0.9779	0.5349	0.9779	0.9889
No log	1.9545	86	0.9679	0.5613	0.9679	0.9838
No log	2.0	88	0.9593	0.5292	0.9593	0.9794
No log	2.0455	90	0.9383	0.5958	0.9383	0.9687
No log	2.0909	92	0.9446	0.5698	0.9446	0.9719
No log	2.1364	94	0.9324	0.6162	0.9324	0.9656
No log	2.1818	96	0.9116	0.6169	0.9116	0.9548
No log	2.2273	98	1.0256	0.6386	1.0256	1.0127
No log	2.2727	100	1.1272	0.5893	1.1272	1.0617
No log	2.3182	102	1.0173	0.6354	1.0173	1.0086
No log	2.3636	104	0.9315	0.6666	0.9315	0.9651
No log	2.4091	106	0.8462	0.6918	0.8462	0.9199
No log	2.4545	108	0.8135	0.6545	0.8135	0.9019
No log	2.5	110	0.7115	0.6872	0.7115	0.8435
No log	2.5455	112	0.6845	0.6907	0.6845	0.8273
No log	2.5909	114	0.8025	0.7026	0.8025	0.8958
No log	2.6364	116	1.2935	0.5561	1.2935	1.1373
No log	2.6818	118	1.6671	0.4972	1.6671	1.2912
No log	2.7273	120	1.5932	0.4764	1.5932	1.2622
No log	2.7727	122	1.2024	0.5866	1.2024	1.0965
No log	2.8182	124	0.9855	0.6315	0.9855	0.9927
No log	2.8636	126	0.9553	0.6504	0.9553	0.9774
No log	2.9091	128	1.2126	0.5948	1.2126	1.1012
No log	2.9545	130	1.5578	0.5130	1.5578	1.2481
No log	3.0	132	1.5098	0.5288	1.5098	1.2287
No log	3.0455	134	1.2112	0.5571	1.2112	1.1005
No log	3.0909	136	0.8896	0.6924	0.8896	0.9432
No log	3.1364	138	0.8154	0.6930	0.8154	0.9030
No log	3.1818	140	0.9093	0.6703	0.9093	0.9536
No log	3.2273	142	1.2419	0.5725	1.2419	1.1144
No log	3.2727	144	1.4317	0.5496	1.4317	1.1965
No log	3.3182	146	1.3878	0.5744	1.3878	1.1780
No log	3.3636	148	1.0642	0.6412	1.0642	1.0316
No log	3.4091	150	0.8351	0.6500	0.8351	0.9138
No log	3.4545	152	0.8353	0.6509	0.8353	0.9140
No log	3.5	154	0.9649	0.6450	0.9649	0.9823
No log	3.5455	156	1.0991	0.6026	1.0991	1.0484
No log	3.5909	158	1.0965	0.6140	1.0965	1.0471
No log	3.6364	160	0.9671	0.6568	0.9671	0.9834
No log	3.6818	162	0.9130	0.6589	0.9130	0.9555
No log	3.7273	164	0.9299	0.6591	0.9299	0.9643
No log	3.7727	166	1.0171	0.6403	1.0171	1.0085
No log	3.8182	168	1.3095	0.5789	1.3095	1.1444
No log	3.8636	170	1.3847	0.5735	1.3847	1.1767
No log	3.9091	172	1.2316	0.5894	1.2316	1.1098
No log	3.9545	174	0.9811	0.6411	0.9811	0.9905
No log	4.0	176	0.8893	0.6291	0.8893	0.9430
No log	4.0455	178	0.9832	0.6242	0.9832	0.9915
No log	4.0909	180	1.1860	0.5913	1.1860	1.0890
No log	4.1364	182	1.3716	0.5541	1.3716	1.1711
No log	4.1818	184	1.3143	0.5580	1.3143	1.1464
No log	4.2273	186	1.2421	0.5873	1.2421	1.1145
No log	4.2727	188	1.0373	0.5971	1.0373	1.0185
No log	4.3182	190	0.8658	0.6206	0.8658	0.9305
No log	4.3636	192	0.8510	0.6185	0.8510	0.9225
No log	4.4091	194	0.9774	0.6237	0.9774	0.9886
No log	4.4545	196	1.2418	0.5909	1.2418	1.1144
No log	4.5	198	1.3617	0.5708	1.3617	1.1669
No log	4.5455	200	1.2293	0.5812	1.2293	1.1087
No log	4.5909	202	1.0878	0.6072	1.0878	1.0430
No log	4.6364	204	0.8526	0.6892	0.8526	0.9233
No log	4.6818	206	0.7726	0.6776	0.7726	0.8790
No log	4.7273	208	0.7126	0.6701	0.7126	0.8442
No log	4.7727	210	0.7127	0.6836	0.7127	0.8442
No log	4.8182	212	0.7999	0.6797	0.7999	0.8944
No log	4.8636	214	0.9678	0.6457	0.9678	0.9838
No log	4.9091	216	1.1934	0.5878	1.1934	1.0924
No log	4.9545	218	1.2902	0.5978	1.2902	1.1359
No log	5.0	220	1.1502	0.6012	1.1502	1.0725
No log	5.0455	222	0.8865	0.6521	0.8865	0.9415
No log	5.0909	224	0.7073	0.6793	0.7073	0.8410
No log	5.1364	226	0.6771	0.6606	0.6771	0.8228
No log	5.1818	228	0.6729	0.6687	0.6729	0.8203
No log	5.2273	230	0.7039	0.7079	0.7039	0.8390
No log	5.2727	232	0.8408	0.6883	0.8408	0.9169
No log	5.3182	234	1.0901	0.6154	1.0901	1.0441
No log	5.3636	236	1.1909	0.6119	1.1909	1.0913
No log	5.4091	238	1.1259	0.6119	1.1259	1.0611
No log	5.4545	240	1.0005	0.6511	1.0005	1.0002
No log	5.5	242	0.9489	0.6570	0.9489	0.9741
No log	5.5455	244	1.0288	0.6328	1.0288	1.0143
No log	5.5909	246	1.1030	0.6314	1.1030	1.0502
No log	5.6364	248	1.1258	0.5884	1.1258	1.0610
No log	5.6818	250	1.0288	0.6270	1.0288	1.0143
No log	5.7273	252	0.9461	0.6305	0.9461	0.9727
No log	5.7727	254	0.8037	0.7152	0.8037	0.8965
No log	5.8182	256	0.7594	0.7239	0.7594	0.8714
No log	5.8636	258	0.7920	0.7239	0.7920	0.8900
No log	5.9091	260	0.8939	0.6585	0.8939	0.9454
No log	5.9545	262	1.0086	0.6538	1.0086	1.0043
No log	6.0	264	1.0771	0.6435	1.0771	1.0378
No log	6.0455	266	1.0031	0.6218	1.0031	1.0016
No log	6.0909	268	0.9074	0.6558	0.9074	0.9526
No log	6.1364	270	0.8650	0.6846	0.8650	0.9300
No log	6.1818	272	0.8797	0.6748	0.8797	0.9379
No log	6.2273	274	0.8427	0.6795	0.8427	0.9180
No log	6.2727	276	0.8203	0.6795	0.8203	0.9057
No log	6.3182	278	0.8339	0.6795	0.8339	0.9132
No log	6.3636	280	0.8597	0.6837	0.8597	0.9272
No log	6.4091	282	0.8605	0.6763	0.8605	0.9276
No log	6.4545	284	0.8713	0.6836	0.8713	0.9334
No log	6.5	286	0.8720	0.7114	0.8720	0.9338
No log	6.5455	288	0.9310	0.6956	0.9310	0.9649
No log	6.5909	290	0.9314	0.7037	0.9314	0.9651
No log	6.6364	292	0.8965	0.7189	0.8965	0.9468
No log	6.6818	294	0.8186	0.6962	0.8186	0.9048
No log	6.7273	296	0.7706	0.7213	0.7706	0.8779
No log	6.7727	298	0.7330	0.7467	0.7330	0.8561
No log	6.8182	300	0.7402	0.7384	0.7402	0.8603
No log	6.8636	302	0.7259	0.7308	0.7259	0.8520
No log	6.9091	304	0.6986	0.7198	0.6986	0.8358
No log	6.9545	306	0.7122	0.6932	0.7122	0.8439
No log	7.0	308	0.7523	0.6869	0.7523	0.8673
No log	7.0455	310	0.7791	0.6611	0.7791	0.8827
No log	7.0909	312	0.8157	0.6734	0.8157	0.9031
No log	7.1364	314	0.8420	0.6742	0.8420	0.9176
No log	7.1818	316	0.8272	0.6857	0.8272	0.9095
No log	7.2273	318	0.7694	0.6741	0.7694	0.8772
No log	7.2727	320	0.7243	0.7121	0.7243	0.8511
No log	7.3182	322	0.7233	0.7140	0.7233	0.8505
No log	7.3636	324	0.7448	0.7259	0.7448	0.8630
No log	7.4091	326	0.7759	0.7294	0.7759	0.8809
No log	7.4545	328	0.8450	0.6922	0.8450	0.9192
No log	7.5	330	0.9426	0.6582	0.9426	0.9709
No log	7.5455	332	0.9890	0.6591	0.9890	0.9945
No log	7.5909	334	1.0620	0.6279	1.0620	1.0305
No log	7.6364	336	1.1383	0.6206	1.1383	1.0669
No log	7.6818	338	1.1335	0.6019	1.1335	1.0647
No log	7.7273	340	1.0888	0.6025	1.0888	1.0434
No log	7.7727	342	1.0043	0.6247	1.0043	1.0022
No log	7.8182	344	0.9565	0.6247	0.9565	0.9780
No log	7.8636	346	0.9430	0.6427	0.9430	0.9711
No log	7.9091	348	0.9512	0.6427	0.9512	0.9753
No log	7.9545	350	0.9752	0.6337	0.9752	0.9875
No log	8.0	352	1.0531	0.6326	1.0531	1.0262
No log	8.0455	354	1.0974	0.6071	1.0974	1.0476
No log	8.0909	356	1.0903	0.6213	1.0903	1.0442
No log	8.1364	358	1.0382	0.6213	1.0382	1.0189
No log	8.1818	360	0.9770	0.6542	0.9770	0.9884
No log	8.2273	362	0.9274	0.6507	0.9274	0.9630
No log	8.2727	364	0.9009	0.6507	0.9009	0.9492
No log	8.3182	366	0.8797	0.6548	0.8797	0.9379
No log	8.3636	368	0.8986	0.6507	0.8986	0.9480
No log	8.4091	370	0.9519	0.6623	0.9519	0.9757
No log	8.4545	372	1.0394	0.6236	1.0394	1.0195
No log	8.5	374	1.0964	0.6114	1.0964	1.0471
No log	8.5455	376	1.0984	0.6114	1.0984	1.0481
No log	8.5909	378	1.0684	0.6155	1.0684	1.0336
No log	8.6364	380	1.0077	0.6208	1.0077	1.0039
No log	8.6818	382	0.9516	0.6451	0.9516	0.9755
No log	8.7273	384	0.9225	0.6529	0.9225	0.9605
No log	8.7727	386	0.9152	0.6496	0.9152	0.9566
No log	8.8182	388	0.9099	0.6538	0.9099	0.9539
No log	8.8636	390	0.9173	0.6289	0.9173	0.9578
No log	8.9091	392	0.9116	0.6420	0.9116	0.9548
No log	8.9545	394	0.9232	0.6289	0.9232	0.9608
No log	9.0	396	0.9407	0.6289	0.9407	0.9699
No log	9.0455	398	0.9814	0.6129	0.9814	0.9907
No log	9.0909	400	1.0092	0.6248	1.0092	1.0046
No log	9.1364	402	1.0128	0.6248	1.0128	1.0064
No log	9.1818	404	1.0132	0.6248	1.0132	1.0066
No log	9.2273	406	1.0037	0.6217	1.0037	1.0019
No log	9.2727	408	0.9935	0.6129	0.9935	0.9967
No log	9.3182	410	0.9861	0.6129	0.9861	0.9930
No log	9.3636	412	0.9748	0.6129	0.9748	0.9873
No log	9.4091	414	0.9645	0.6129	0.9645	0.9821
No log	9.4545	416	0.9548	0.6215	0.9548	0.9771
No log	9.5	418	0.9594	0.6129	0.9594	0.9795
No log	9.5455	420	0.9675	0.6129	0.9675	0.9836
No log	9.5909	422	0.9745	0.6129	0.9745	0.9872
No log	9.6364	424	0.9867	0.6129	0.9867	0.9933
No log	9.6818	426	0.9943	0.6129	0.9943	0.9972
No log	9.7273	428	0.9971	0.6129	0.9971	0.9986
No log	9.7727	430	0.9991	0.6129	0.9991	0.9996
No log	9.8182	432	0.9986	0.6161	0.9986	0.9993
No log	9.8636	434	0.9992	0.6161	0.9992	0.9996
No log	9.9091	436	1.0005	0.6161	1.0005	1.0002
No log	9.9545	438	1.0003	0.6161	1.0003	1.0002
No log	10.0	440	0.9997	0.6161	0.9997	0.9998

Framework versions

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