ArabicNewSplits4_WithDuplicationsForScore5_FineTuningAraBERT_run2_AugV5_k4_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: 1.1668
• Qwk: 0.6020
• Mse: 1.1668
• Rmse: 1.0802

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	0.125	2	2.3617	0.0485	2.3617	1.5368
No log	0.25	4	1.5190	0.1917	1.5190	1.2325
No log	0.375	6	1.3241	0.1715	1.3241	1.1507
No log	0.5	8	1.5951	0.3102	1.5951	1.2630
No log	0.625	10	1.6379	0.2858	1.6379	1.2798
No log	0.75	12	1.6692	0.3071	1.6692	1.2920
No log	0.875	14	1.6345	0.3276	1.6345	1.2785
No log	1.0	16	1.5665	0.3807	1.5665	1.2516
No log	1.125	18	1.4610	0.3612	1.4610	1.2087
No log	1.25	20	1.4717	0.3671	1.4717	1.2131
No log	1.375	22	1.5432	0.4001	1.5432	1.2422
No log	1.5	24	1.6780	0.3576	1.6780	1.2954
No log	1.625	26	1.8114	0.3190	1.8114	1.3459
No log	1.75	28	1.6944	0.3467	1.6944	1.3017
No log	1.875	30	1.5160	0.3139	1.5160	1.2313
No log	2.0	32	1.4904	0.3139	1.4904	1.2208
No log	2.125	34	1.6446	0.3670	1.6446	1.2824
No log	2.25	36	2.0473	0.3286	2.0473	1.4308
No log	2.375	38	2.0742	0.3203	2.0742	1.4402
No log	2.5	40	1.9029	0.3655	1.9029	1.3795
No log	2.625	42	1.5877	0.4515	1.5877	1.2600
No log	2.75	44	1.3006	0.4810	1.3006	1.1404
No log	2.875	46	1.2609	0.4204	1.2609	1.1229
No log	3.0	48	1.3866	0.4669	1.3866	1.1775
No log	3.125	50	1.7218	0.4361	1.7218	1.3122
No log	3.25	52	2.0334	0.3776	2.0334	1.4260
No log	3.375	54	1.9713	0.4055	1.9713	1.4040
No log	3.5	56	1.8271	0.4337	1.8271	1.3517
No log	3.625	58	1.6115	0.4658	1.6115	1.2695
No log	3.75	60	1.3074	0.5228	1.3074	1.1434
No log	3.875	62	1.1998	0.5542	1.1998	1.0953
No log	4.0	64	1.2606	0.5240	1.2606	1.1228
No log	4.125	66	1.3676	0.5221	1.3676	1.1695
No log	4.25	68	1.4847	0.4941	1.4847	1.2185
No log	4.375	70	1.5988	0.4894	1.5988	1.2644
No log	4.5	72	1.6298	0.4717	1.6298	1.2766
No log	4.625	74	1.5709	0.4759	1.5709	1.2534
No log	4.75	76	1.4221	0.5117	1.4221	1.1925
No log	4.875	78	1.2460	0.5641	1.2460	1.1162
No log	5.0	80	1.1758	0.5703	1.1758	1.0843
No log	5.125	82	1.1979	0.5726	1.1979	1.0945
No log	5.25	84	1.2796	0.5801	1.2796	1.1312
No log	5.375	86	1.2782	0.5676	1.2782	1.1306
No log	5.5	88	1.2040	0.5738	1.2040	1.0973
No log	5.625	90	1.1769	0.5704	1.1769	1.0848
No log	5.75	92	1.1844	0.5542	1.1844	1.0883
No log	5.875	94	1.2530	0.5603	1.2530	1.1194
No log	6.0	96	1.2587	0.5886	1.2587	1.1219
No log	6.125	98	1.2010	0.5886	1.2010	1.0959
No log	6.25	100	1.1833	0.5759	1.1833	1.0878
No log	6.375	102	1.1554	0.5661	1.1554	1.0749
No log	6.5	104	1.0656	0.5758	1.0656	1.0323
No log	6.625	106	1.0151	0.5905	1.0151	1.0075
No log	6.75	108	1.0487	0.6169	1.0487	1.0241
No log	6.875	110	1.0992	0.5930	1.0992	1.0484
No log	7.0	112	1.1648	0.5809	1.1648	1.0792
No log	7.125	114	1.2250	0.5654	1.2250	1.1068
No log	7.25	116	1.2732	0.5644	1.2732	1.1283
No log	7.375	118	1.2756	0.5799	1.2756	1.1294
No log	7.5	120	1.2328	0.5871	1.2328	1.1103
No log	7.625	122	1.1557	0.5905	1.1557	1.0750
No log	7.75	124	1.0840	0.5966	1.0840	1.0411
No log	7.875	126	1.0329	0.6003	1.0329	1.0163
No log	8.0	128	0.9997	0.6232	0.9997	0.9998
No log	8.125	130	0.9908	0.6011	0.9908	0.9954
No log	8.25	132	1.0288	0.5978	1.0288	1.0143
No log	8.375	134	1.0702	0.5978	1.0702	1.0345
No log	8.5	136	1.1185	0.6002	1.1185	1.0576
No log	8.625	138	1.1794	0.6023	1.1794	1.0860
No log	8.75	140	1.2234	0.5973	1.2234	1.1061
No log	8.875	142	1.2314	0.5973	1.2314	1.1097
No log	9.0	144	1.2334	0.5932	1.2334	1.1106
No log	9.125	146	1.2301	0.5871	1.2301	1.1091
No log	9.25	148	1.2221	0.5871	1.2221	1.1055
No log	9.375	150	1.2157	0.5871	1.2157	1.1026
No log	9.5	152	1.2043	0.5871	1.2043	1.0974
No log	9.625	154	1.1910	0.5937	1.1910	1.0913
No log	9.75	156	1.1817	0.5937	1.1817	1.0871
No log	9.875	158	1.1721	0.5979	1.1721	1.0826
No log	10.0	160	1.1668	0.6020	1.1668	1.0802

Framework versions

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