ArabicNewSplits6_FineTuningAraBERT_run3_AugV5_k10_task3_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: 0.5985
• Qwk: 0.4930
• Mse: 0.5985
• Rmse: 0.7736

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	0.0417	2	3.3751	-0.0053	3.3751	1.8372
No log	0.0833	4	2.5268	-0.1082	2.5268	1.5896
No log	0.125	6	1.0875	0.0	1.0875	1.0428
No log	0.1667	8	0.9012	0.0476	0.9012	0.9493
No log	0.2083	10	0.7501	0.0980	0.7501	0.8661
No log	0.25	12	0.8934	0.0380	0.8934	0.9452
No log	0.2917	14	0.8699	0.0085	0.8699	0.9327
No log	0.3333	16	0.9620	0.0617	0.9620	0.9808
No log	0.375	18	1.2232	0.0078	1.2232	1.1060
No log	0.4167	20	0.9158	0.0685	0.9158	0.9570
No log	0.4583	22	0.7060	-0.1014	0.7060	0.8402
No log	0.5	24	0.6807	-0.0233	0.6807	0.8250
No log	0.5417	26	0.7055	0.0	0.7055	0.8399
No log	0.5833	28	0.6724	0.0	0.6724	0.8200
No log	0.625	30	0.6333	0.1795	0.6333	0.7958
No log	0.6667	32	0.9555	0.0578	0.9555	0.9775
No log	0.7083	34	0.6257	0.2201	0.6257	0.7910
No log	0.75	36	0.5650	0.2533	0.5650	0.7517
No log	0.7917	38	0.5519	0.2941	0.5519	0.7429
No log	0.8333	40	0.5745	0.125	0.5745	0.7580
No log	0.875	42	0.5560	0.1642	0.5560	0.7457
No log	0.9167	44	0.6868	0.3089	0.6868	0.8287
No log	0.9583	46	0.6141	0.3882	0.6141	0.7837
No log	1.0	48	0.5349	0.2727	0.5349	0.7313
No log	1.0417	50	0.7232	0.1568	0.7232	0.8504
No log	1.0833	52	0.5685	0.2752	0.5685	0.7540
No log	1.125	54	0.7461	0.1770	0.7461	0.8637
No log	1.1667	56	0.8848	0.1588	0.8848	0.9406
No log	1.2083	58	0.5738	0.2093	0.5738	0.7575
No log	1.25	60	0.7405	0.2000	0.7405	0.8605
No log	1.2917	62	0.9544	-0.0545	0.9544	0.9770
No log	1.3333	64	0.8206	0.0629	0.8206	0.9059
No log	1.375	66	0.6483	0.1135	0.6483	0.8052
No log	1.4167	68	1.1976	0.0745	1.1976	1.0943
No log	1.4583	70	1.1815	0.0698	1.1815	1.0869
No log	1.5	72	0.8083	0.1667	0.8083	0.8991
No log	1.5417	74	0.6155	0.0877	0.6155	0.7845
No log	1.5833	76	0.6391	0.2552	0.6391	0.7995
No log	1.625	78	0.8042	0.2444	0.8042	0.8968
No log	1.6667	80	0.6948	0.2970	0.6948	0.8335
No log	1.7083	82	0.5866	0.2090	0.5866	0.7659
No log	1.75	84	1.1790	0.1206	1.1790	1.0858
No log	1.7917	86	1.3099	0.1351	1.3099	1.1445
No log	1.8333	88	0.8163	0.1644	0.8163	0.9035
No log	1.875	90	0.5658	0.4286	0.5658	0.7522
No log	1.9167	92	0.9056	0.0154	0.9056	0.9516
No log	1.9583	94	0.8988	0.0431	0.8988	0.9481
No log	2.0	96	0.6143	0.2533	0.6143	0.7838
No log	2.0417	98	0.5210	0.2632	0.5210	0.7218
No log	2.0833	100	0.5389	0.2683	0.5389	0.7341
No log	2.125	102	0.5291	0.3846	0.5291	0.7274
No log	2.1667	104	0.6971	0.3757	0.6971	0.8349
No log	2.2083	106	0.6481	0.4105	0.6481	0.8050
No log	2.25	108	0.6321	0.3814	0.6321	0.7951
No log	2.2917	110	0.6325	0.3684	0.6325	0.7953
No log	2.3333	112	0.7728	0.2618	0.7728	0.8791
No log	2.375	114	0.8747	0.2389	0.8747	0.9353
No log	2.4167	116	0.7447	0.3004	0.7447	0.8630
No log	2.4583	118	0.6477	0.3089	0.6477	0.8048
No log	2.5	120	0.6202	0.3231	0.6202	0.7875
No log	2.5417	122	0.6330	0.4128	0.6330	0.7956
No log	2.5833	124	0.8693	0.1939	0.8693	0.9324
No log	2.625	126	0.6504	0.3422	0.6504	0.8064
No log	2.6667	128	0.6166	0.2593	0.6166	0.7852
No log	2.7083	130	0.8233	0.1289	0.8233	0.9073
No log	2.75	132	0.6142	0.2889	0.6142	0.7837
No log	2.7917	134	0.6423	0.2727	0.6423	0.8015
No log	2.8333	136	0.8910	0.2327	0.8910	0.9439
No log	2.875	138	0.6939	0.2637	0.6939	0.8330
No log	2.9167	140	0.5661	0.3224	0.5661	0.7524
No log	2.9583	142	0.6585	0.1818	0.6585	0.8115
No log	3.0	144	0.6267	0.3478	0.6267	0.7917
No log	3.0417	146	0.7265	0.3818	0.7265	0.8523
No log	3.0833	148	0.8380	0.4050	0.8380	0.9154
No log	3.125	150	0.9467	0.2440	0.9467	0.9730
No log	3.1667	152	0.7035	0.4087	0.7035	0.8387
No log	3.2083	154	0.6071	0.3333	0.6071	0.7792
No log	3.25	156	0.6553	0.3755	0.6553	0.8095
No log	3.2917	158	0.6382	0.3898	0.6382	0.7989
No log	3.3333	160	0.5724	0.3874	0.5724	0.7566
No log	3.375	162	0.7635	0.3846	0.7635	0.8738
No log	3.4167	164	1.1454	0.0915	1.1454	1.0702
No log	3.4583	166	1.2132	0.0035	1.2132	1.1014
No log	3.5	168	1.0040	0.1014	1.0040	1.0020
No log	3.5417	170	0.7376	0.3214	0.7376	0.8588
No log	3.5833	172	0.6075	0.4231	0.6075	0.7794
No log	3.625	174	0.6312	0.4231	0.6312	0.7945
No log	3.6667	176	0.8232	0.3202	0.8232	0.9073
No log	3.7083	178	1.1661	0.1429	1.1661	1.0799
No log	3.75	180	1.5818	0.0968	1.5818	1.2577
No log	3.7917	182	1.3642	0.1553	1.3642	1.1680
No log	3.8333	184	0.9188	0.3282	0.9188	0.9585
No log	3.875	186	0.8171	0.3036	0.8171	0.9039
No log	3.9167	188	0.8656	0.2846	0.8656	0.9304
No log	3.9583	190	0.9581	0.2481	0.9581	0.9788
No log	4.0	192	1.0230	0.1254	1.0230	1.0114
No log	4.0417	194	0.9845	0.1533	0.9845	0.9922
No log	4.0833	196	1.0352	0.1886	1.0352	1.0175
No log	4.125	198	0.7445	0.3633	0.7445	0.8628
No log	4.1667	200	0.6191	0.3524	0.6191	0.7868
No log	4.2083	202	0.6777	0.3833	0.6777	0.8232
No log	4.25	204	0.7868	0.3333	0.7868	0.8870
No log	4.2917	206	0.8177	0.3903	0.8177	0.9043
No log	4.3333	208	0.9940	0.1667	0.9940	0.9970
No log	4.375	210	0.8802	0.2958	0.8802	0.9382
No log	4.4167	212	0.6237	0.4340	0.6237	0.7897
No log	4.4583	214	0.6026	0.4010	0.6026	0.7763
No log	4.5	216	0.8355	0.2647	0.8355	0.9141
No log	4.5417	218	0.9705	0.2688	0.9705	0.9851
No log	4.5833	220	0.8742	0.2582	0.8742	0.9350
No log	4.625	222	0.9810	0.2113	0.9810	0.9904
No log	4.6667	224	0.8314	0.2582	0.8314	0.9118
No log	4.7083	226	0.6606	0.4335	0.6606	0.8128
No log	4.75	228	0.5773	0.3761	0.5773	0.7598
No log	4.7917	230	0.5978	0.4182	0.5978	0.7732
No log	4.8333	232	0.7223	0.3834	0.7223	0.8499
No log	4.875	234	0.9839	0.1943	0.9839	0.9919
No log	4.9167	236	0.9611	0.2340	0.9611	0.9803
No log	4.9583	238	0.6890	0.3719	0.6890	0.8301
No log	5.0	240	0.5990	0.3665	0.5990	0.7739
No log	5.0417	242	0.6114	0.3247	0.6114	0.7819
No log	5.0833	244	0.8652	0.3429	0.8652	0.9301
No log	5.125	246	1.3673	0.0933	1.3673	1.1693
No log	5.1667	248	1.2876	0.1186	1.2876	1.1347
No log	5.2083	250	0.8043	0.2959	0.8043	0.8968
No log	5.25	252	0.5253	0.3892	0.5253	0.7248
No log	5.2917	254	0.5234	0.3508	0.5234	0.7235
No log	5.3333	256	0.5210	0.4043	0.5210	0.7218
No log	5.375	258	0.6754	0.3080	0.6754	0.8218
No log	5.4167	260	0.7545	0.2248	0.7545	0.8686
No log	5.4583	262	0.5987	0.4286	0.5987	0.7737
No log	5.5	264	0.4955	0.4098	0.4955	0.7039
No log	5.5417	266	0.4999	0.4595	0.4999	0.7071
No log	5.5833	268	0.5513	0.4286	0.5513	0.7425
No log	5.625	270	0.6513	0.3414	0.6513	0.8070
No log	5.6667	272	0.6431	0.3414	0.6431	0.8019
No log	5.7083	274	0.5911	0.3846	0.5911	0.7688
No log	5.75	276	0.5634	0.3833	0.5634	0.7506
No log	5.7917	278	0.5754	0.3929	0.5754	0.7585
No log	5.8333	280	0.6441	0.3388	0.6441	0.8026
No log	5.875	282	0.7140	0.3359	0.7140	0.8450
No log	5.9167	284	0.5750	0.4341	0.5750	0.7583
No log	5.9583	286	0.5227	0.4563	0.5227	0.7230
No log	6.0	288	0.4535	0.4098	0.4535	0.6735
No log	6.0417	290	0.4565	0.4583	0.4565	0.6757
No log	6.0833	292	0.4733	0.4462	0.4733	0.6880
No log	6.125	294	0.6607	0.3016	0.6607	0.8128
No log	6.1667	296	0.8082	0.3309	0.8082	0.8990
No log	6.2083	298	0.6953	0.3359	0.6953	0.8338
No log	6.25	300	0.5428	0.5468	0.5428	0.7368
No log	6.2917	302	0.4609	0.4462	0.4609	0.6789
No log	6.3333	304	0.4532	0.4098	0.4532	0.6732
No log	6.375	306	0.4809	0.4462	0.4809	0.6934
No log	6.4167	308	0.5815	0.4286	0.5815	0.7626
No log	6.4583	310	0.6703	0.3080	0.6703	0.8187
No log	6.5	312	0.6535	0.3874	0.6535	0.8084
No log	6.5417	314	0.6452	0.3874	0.6452	0.8032
No log	6.5833	316	0.5900	0.4495	0.5900	0.7681
No log	6.625	318	0.5184	0.48	0.5184	0.7200
No log	6.6667	320	0.4946	0.48	0.4946	0.7033
No log	6.7083	322	0.5293	0.5102	0.5293	0.7276
No log	6.75	324	0.6334	0.3874	0.6334	0.7959
No log	6.7917	326	0.6839	0.2863	0.6839	0.8270
No log	6.8333	328	0.6079	0.3645	0.6079	0.7797
No log	6.875	330	0.4950	0.5847	0.4950	0.7036
No log	6.9167	332	0.4595	0.4419	0.4595	0.6779
No log	6.9583	334	0.4573	0.3295	0.4573	0.6762
No log	7.0	336	0.4608	0.4419	0.4608	0.6788
No log	7.0417	338	0.5178	0.5233	0.5178	0.7196
No log	7.0833	340	0.5917	0.3917	0.5917	0.7692
No log	7.125	342	0.5579	0.4554	0.5579	0.7469
No log	7.1667	344	0.5357	0.5468	0.5357	0.7319
No log	7.2083	346	0.5726	0.4495	0.5726	0.7567
No log	7.25	348	0.6419	0.3388	0.6419	0.8012
No log	7.2917	350	0.5903	0.4495	0.5903	0.7683
No log	7.3333	352	0.5295	0.5294	0.5295	0.7276
No log	7.375	354	0.4902	0.5330	0.4902	0.7001
No log	7.4167	356	0.5008	0.5464	0.5008	0.7077
No log	7.4583	358	0.5485	0.5556	0.5485	0.7406
No log	7.5	360	0.5836	0.4924	0.5836	0.7639
No log	7.5417	362	0.5489	0.5282	0.5489	0.7409
No log	7.5833	364	0.5545	0.5	0.5545	0.7447
No log	7.625	366	0.6125	0.4171	0.6125	0.7826
No log	7.6667	368	0.7075	0.2520	0.7075	0.8411
No log	7.7083	370	0.7805	0.2248	0.7805	0.8835
No log	7.75	372	0.7617	0.25	0.7617	0.8727
No log	7.7917	374	0.6370	0.4138	0.6370	0.7981
No log	7.8333	376	0.5402	0.4902	0.5402	0.7350
No log	7.875	378	0.5028	0.4043	0.5028	0.7091
No log	7.9167	380	0.5173	0.4162	0.5173	0.7192
No log	7.9583	382	0.5308	0.4573	0.5308	0.7285
No log	8.0	384	0.5796	0.5074	0.5796	0.7613
No log	8.0417	386	0.6937	0.3414	0.6937	0.8329
No log	8.0833	388	0.7202	0.3414	0.7202	0.8487
No log	8.125	390	0.6654	0.3846	0.6654	0.8157
No log	8.1667	392	0.5703	0.4872	0.5703	0.7552
No log	8.2083	394	0.5398	0.5183	0.5398	0.7347
No log	8.25	396	0.5416	0.5648	0.5416	0.7359
No log	8.2917	398	0.5530	0.4872	0.5530	0.7437
No log	8.3333	400	0.6103	0.3725	0.6103	0.7812
No log	8.375	402	0.6743	0.3473	0.6743	0.8212
No log	8.4167	404	0.7086	0.2863	0.7086	0.8418
No log	8.4583	406	0.6642	0.3504	0.6642	0.8150
No log	8.5	408	0.6053	0.4171	0.6053	0.7780
No log	8.5417	410	0.5589	0.4872	0.5589	0.7476
No log	8.5833	412	0.5109	0.5602	0.5109	0.7148
No log	8.625	414	0.4987	0.5359	0.4987	0.7062
No log	8.6667	416	0.5087	0.5602	0.5087	0.7133
No log	8.7083	418	0.5321	0.5648	0.5321	0.7294
No log	8.75	420	0.5606	0.4872	0.5606	0.7488
No log	8.7917	422	0.5786	0.48	0.5786	0.7606
No log	8.8333	424	0.5958	0.4171	0.5958	0.7719
No log	8.875	426	0.6180	0.4019	0.6180	0.7861
No log	8.9167	428	0.6381	0.3929	0.6381	0.7988
No log	8.9583	430	0.6190	0.4019	0.6190	0.7867
No log	9.0	432	0.6106	0.3684	0.6106	0.7814
No log	9.0417	434	0.6001	0.4396	0.6001	0.7746
No log	9.0833	436	0.5923	0.4930	0.5923	0.7696
No log	9.125	438	0.5835	0.5	0.5835	0.7639
No log	9.1667	440	0.5953	0.4930	0.5953	0.7716
No log	9.2083	442	0.5998	0.4930	0.5998	0.7745
No log	9.25	444	0.5766	0.4882	0.5766	0.7594
No log	9.2917	446	0.5634	0.4882	0.5634	0.7506
No log	9.3333	448	0.5696	0.4882	0.5696	0.7547
No log	9.375	450	0.5875	0.4930	0.5875	0.7665
No log	9.4167	452	0.6028	0.4930	0.6028	0.7764
No log	9.4583	454	0.6129	0.4930	0.6129	0.7829
No log	9.5	456	0.6161	0.4667	0.6161	0.7849
No log	9.5417	458	0.6138	0.4667	0.6138	0.7834
No log	9.5833	460	0.6035	0.4930	0.6035	0.7768
No log	9.625	462	0.5851	0.5	0.5851	0.7649
No log	9.6667	464	0.5725	0.5	0.5725	0.7567
No log	9.7083	466	0.5683	0.4882	0.5683	0.7539
No log	9.75	468	0.5698	0.4882	0.5698	0.7549
No log	9.7917	470	0.5694	0.4882	0.5694	0.7546
No log	9.8333	472	0.5764	0.5	0.5764	0.7592
No log	9.875	474	0.5860	0.5	0.5860	0.7655
No log	9.9167	476	0.5936	0.5	0.5936	0.7705
No log	9.9583	478	0.5974	0.4930	0.5974	0.7729
No log	10.0	480	0.5985	0.4930	0.5985	0.7736

Framework versions

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