ArabicNewSplits7_usingALLEssays_FineTuningAraBERT_run1_AugV5_k2_task7_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: 0.5124
• Qwk: 0.5920
• Mse: 0.5124
• Rmse: 0.7158

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: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.2	2	2.5156	-0.0109	2.5156	1.5861
No log	0.4	4	1.2162	0.1265	1.2162	1.1028
No log	0.6	6	0.7642	0.1372	0.7642	0.8742
No log	0.8	8	0.7164	0.0	0.7164	0.8464
No log	1.0	10	0.7258	0.0327	0.7258	0.8519
No log	1.2	12	0.7431	0.1866	0.7431	0.8620
No log	1.4	14	0.7394	0.2652	0.7394	0.8599
No log	1.6	16	0.7466	0.0481	0.7466	0.8641
No log	1.8	18	0.8772	0.1339	0.8772	0.9366
No log	2.0	20	0.9890	0.3425	0.9890	0.9945
No log	2.2	22	0.9466	0.3085	0.9466	0.9729
No log	2.4	24	0.6773	0.2132	0.6773	0.8230
No log	2.6	26	0.5948	0.3518	0.5948	0.7712
No log	2.8	28	0.6609	0.3675	0.6609	0.8130
No log	3.0	30	0.6198	0.3425	0.6198	0.7872
No log	3.2	32	0.5373	0.5208	0.5373	0.7330
No log	3.4	34	0.7013	0.4357	0.7013	0.8374
No log	3.6	36	0.7812	0.3119	0.7812	0.8839
No log	3.8	38	0.8517	0.2651	0.8517	0.9229
No log	4.0	40	0.7281	0.3825	0.7281	0.8533
No log	4.2	42	0.5643	0.4388	0.5643	0.7512
No log	4.4	44	0.5988	0.2930	0.5988	0.7738
No log	4.6	46	0.6466	0.3166	0.6466	0.8041
No log	4.8	48	0.6393	0.2819	0.6393	0.7995
No log	5.0	50	0.5959	0.4060	0.5959	0.7719
No log	5.2	52	0.5626	0.4060	0.5626	0.7501
No log	5.4	54	0.5817	0.4060	0.5817	0.7627
No log	5.6	56	0.5831	0.3416	0.5831	0.7636
No log	5.8	58	0.5836	0.3258	0.5836	0.7639
No log	6.0	60	0.7355	0.4142	0.7355	0.8576
No log	6.2	62	0.8562	0.2627	0.8562	0.9253
No log	6.4	64	0.7463	0.3938	0.7463	0.8639
No log	6.6	66	0.5863	0.4841	0.5863	0.7657
No log	6.8	68	0.5152	0.5095	0.5152	0.7178
No log	7.0	70	0.6806	0.4199	0.6806	0.8250
No log	7.2	72	0.8097	0.4698	0.8097	0.8998
No log	7.4	74	0.7640	0.4513	0.7640	0.8741
No log	7.6	76	0.6420	0.4662	0.6420	0.8012
No log	7.8	78	0.5982	0.4929	0.5982	0.7734
No log	8.0	80	0.6144	0.5079	0.6144	0.7839
No log	8.2	82	0.6435	0.4499	0.6435	0.8022
No log	8.4	84	0.6030	0.5692	0.6030	0.7765
No log	8.6	86	0.5298	0.5538	0.5298	0.7279
No log	8.8	88	0.4919	0.5556	0.4919	0.7014
No log	9.0	90	0.5295	0.5991	0.5295	0.7277
No log	9.2	92	0.5515	0.5511	0.5515	0.7426
No log	9.4	94	0.5027	0.5273	0.5027	0.7090
No log	9.6	96	0.4928	0.5846	0.4928	0.7020
No log	9.8	98	0.5359	0.5869	0.5359	0.7321
No log	10.0	100	0.7312	0.4977	0.7312	0.8551
No log	10.2	102	0.8182	0.4151	0.8182	0.9045
No log	10.4	104	0.6474	0.5723	0.6474	0.8046
No log	10.6	106	0.5261	0.6248	0.5261	0.7253
No log	10.8	108	0.5030	0.4972	0.5030	0.7092
No log	11.0	110	0.5231	0.5550	0.5231	0.7233
No log	11.2	112	0.5069	0.5472	0.5069	0.7120
No log	11.4	114	0.4778	0.6017	0.4778	0.6912
No log	11.6	116	0.5576	0.6027	0.5576	0.7467
No log	11.8	118	0.5866	0.5460	0.5866	0.7659
No log	12.0	120	0.4897	0.6326	0.4897	0.6998
No log	12.2	122	0.4844	0.5738	0.4844	0.6960
No log	12.4	124	0.5759	0.5468	0.5759	0.7589
No log	12.6	126	0.5566	0.6118	0.5566	0.7460
No log	12.8	128	0.4980	0.6096	0.4980	0.7057
No log	13.0	130	0.5050	0.6084	0.5050	0.7106
No log	13.2	132	0.5971	0.5240	0.5971	0.7727
No log	13.4	134	0.5766	0.5297	0.5766	0.7594
No log	13.6	136	0.5069	0.5893	0.5069	0.7119
No log	13.8	138	0.5160	0.5912	0.5160	0.7183
No log	14.0	140	0.5856	0.5909	0.5856	0.7652
No log	14.2	142	0.6010	0.5752	0.6010	0.7753
No log	14.4	144	0.5895	0.5882	0.5895	0.7678
No log	14.6	146	0.5413	0.5897	0.5413	0.7357
No log	14.8	148	0.5100	0.5738	0.5100	0.7141
No log	15.0	150	0.4988	0.6087	0.4988	0.7063
No log	15.2	152	0.5724	0.6406	0.5724	0.7565
No log	15.4	154	0.5784	0.6146	0.5784	0.7605
No log	15.6	156	0.5531	0.5848	0.5531	0.7437
No log	15.8	158	0.5195	0.5692	0.5195	0.7207
No log	16.0	160	0.5296	0.5647	0.5296	0.7277
No log	16.2	162	0.5776	0.4788	0.5776	0.7600
No log	16.4	164	0.7052	0.4153	0.7052	0.8398
No log	16.6	166	0.8371	0.4021	0.8371	0.9149
No log	16.8	168	0.8042	0.5017	0.8042	0.8968
No log	17.0	170	0.5930	0.6005	0.5930	0.7700
No log	17.2	172	0.4911	0.5888	0.4911	0.7008
No log	17.4	174	0.6011	0.5579	0.6011	0.7753
No log	17.6	176	0.8059	0.4260	0.8059	0.8977
No log	17.8	178	0.9074	0.3649	0.9074	0.9526
No log	18.0	180	0.7885	0.4260	0.7885	0.8880
No log	18.2	182	0.5997	0.5478	0.5997	0.7744
No log	18.4	184	0.5008	0.6286	0.5008	0.7077
No log	18.6	186	0.5591	0.5991	0.5591	0.7477
No log	18.8	188	0.5670	0.5342	0.5670	0.7530
No log	19.0	190	0.5513	0.5379	0.5513	0.7425
No log	19.2	192	0.5200	0.5395	0.5200	0.7211
No log	19.4	194	0.5147	0.5756	0.5147	0.7174
No log	19.6	196	0.5203	0.6100	0.5203	0.7213
No log	19.8	198	0.5245	0.6284	0.5245	0.7242
No log	20.0	200	0.5375	0.5769	0.5375	0.7331
No log	20.2	202	0.5426	0.5835	0.5426	0.7366
No log	20.4	204	0.5446	0.5809	0.5446	0.7379
No log	20.6	206	0.5319	0.5953	0.5319	0.7293
No log	20.8	208	0.5217	0.5929	0.5217	0.7223
No log	21.0	210	0.5147	0.5444	0.5147	0.7174
No log	21.2	212	0.5249	0.5289	0.5249	0.7245
No log	21.4	214	0.5309	0.5042	0.5309	0.7287
No log	21.6	216	0.5395	0.4788	0.5395	0.7345
No log	21.8	218	0.5290	0.5123	0.5290	0.7273
No log	22.0	220	0.5508	0.5712	0.5508	0.7422
No log	22.2	222	0.6026	0.5659	0.6026	0.7763
No log	22.4	224	0.5487	0.5624	0.5487	0.7407
No log	22.6	226	0.4756	0.6018	0.4756	0.6896
No log	22.8	228	0.4834	0.5714	0.4834	0.6953
No log	23.0	230	0.4839	0.5633	0.4839	0.6956
No log	23.2	232	0.4606	0.6228	0.4606	0.6787
No log	23.4	234	0.4884	0.5897	0.4884	0.6988
No log	23.6	236	0.5257	0.5814	0.5257	0.7251
No log	23.8	238	0.4879	0.5897	0.4879	0.6985
No log	24.0	240	0.4635	0.5874	0.4635	0.6808
No log	24.2	242	0.4692	0.6515	0.4692	0.6850
No log	24.4	244	0.4716	0.6526	0.4716	0.6868
No log	24.6	246	0.4628	0.6007	0.4628	0.6803
No log	24.8	248	0.4807	0.6970	0.4807	0.6933
No log	25.0	250	0.5230	0.6206	0.5230	0.7232
No log	25.2	252	0.5108	0.6283	0.5108	0.7147
No log	25.4	254	0.5000	0.6206	0.5000	0.7071
No log	25.6	256	0.4981	0.6459	0.4981	0.7058
No log	25.8	258	0.4974	0.6459	0.4974	0.7053
No log	26.0	260	0.4966	0.6459	0.4966	0.7047
No log	26.2	262	0.4855	0.6617	0.4855	0.6968
No log	26.4	264	0.4762	0.6454	0.4762	0.6901
No log	26.6	266	0.4822	0.6464	0.4822	0.6944
No log	26.8	268	0.4875	0.6394	0.4875	0.6982
No log	27.0	270	0.5196	0.6117	0.5196	0.7208
No log	27.2	272	0.4986	0.6703	0.4986	0.7061
No log	27.4	274	0.4722	0.6989	0.4722	0.6872
No log	27.6	276	0.4696	0.6989	0.4696	0.6853
No log	27.8	278	0.4696	0.6850	0.4696	0.6853
No log	28.0	280	0.4641	0.6927	0.4641	0.6813
No log	28.2	282	0.4710	0.6784	0.4710	0.6863
No log	28.4	284	0.4819	0.6784	0.4819	0.6942
No log	28.6	286	0.4978	0.6700	0.4978	0.7055
No log	28.8	288	0.5045	0.6768	0.5045	0.7103
No log	29.0	290	0.5282	0.6335	0.5282	0.7268
No log	29.2	292	0.5973	0.5779	0.5973	0.7728
No log	29.4	294	0.6517	0.5551	0.6517	0.8073
No log	29.6	296	0.5584	0.5910	0.5584	0.7473
No log	29.8	298	0.4819	0.6803	0.4819	0.6942
No log	30.0	300	0.4469	0.6953	0.4469	0.6685
No log	30.2	302	0.4396	0.6552	0.4396	0.6630
No log	30.4	304	0.4679	0.5983	0.4679	0.6840
No log	30.6	306	0.4838	0.5991	0.4838	0.6955
No log	30.8	308	0.4720	0.5729	0.4720	0.6870
No log	31.0	310	0.4665	0.6484	0.4665	0.6830
No log	31.2	312	0.4641	0.7004	0.4641	0.6813
No log	31.4	314	0.4660	0.7086	0.4660	0.6826
No log	31.6	316	0.4736	0.7086	0.4736	0.6882
No log	31.8	318	0.5062	0.7022	0.5062	0.7115
No log	32.0	320	0.4970	0.6886	0.4970	0.7050
No log	32.2	322	0.4634	0.6845	0.4634	0.6808
No log	32.4	324	0.4526	0.7022	0.4526	0.6728
No log	32.6	326	0.4516	0.6662	0.4516	0.6720
No log	32.8	328	0.4524	0.7004	0.4524	0.6726
No log	33.0	330	0.4580	0.7004	0.4580	0.6768
No log	33.2	332	0.4678	0.6923	0.4678	0.6840
No log	33.4	334	0.4793	0.6613	0.4793	0.6923
No log	33.6	336	0.4665	0.7004	0.4665	0.6830
No log	33.8	338	0.4856	0.6623	0.4856	0.6969
No log	34.0	340	0.5162	0.6271	0.5162	0.7185
No log	34.2	342	0.5196	0.5683	0.5196	0.7208
No log	34.4	344	0.4776	0.7110	0.4776	0.6911
No log	34.6	346	0.4724	0.7041	0.4724	0.6873
No log	34.8	348	0.4751	0.6676	0.4751	0.6893
No log	35.0	350	0.4840	0.6676	0.4840	0.6957
No log	35.2	352	0.4876	0.6823	0.4876	0.6982
No log	35.4	354	0.4906	0.6823	0.4906	0.7004
No log	35.6	356	0.4903	0.6974	0.4903	0.7002
No log	35.8	358	0.4917	0.6897	0.4917	0.7012
No log	36.0	360	0.5084	0.6639	0.5084	0.7130
No log	36.2	362	0.5309	0.5888	0.5309	0.7286
No log	36.4	364	0.5184	0.5587	0.5184	0.7200
No log	36.6	366	0.4842	0.5679	0.4842	0.6958
No log	36.8	368	0.4677	0.6185	0.4677	0.6839
No log	37.0	370	0.4803	0.6491	0.4803	0.6931
No log	37.2	372	0.4937	0.6526	0.4937	0.7027
No log	37.4	374	0.4914	0.7086	0.4914	0.7010
No log	37.6	376	0.4956	0.7147	0.4956	0.7040
No log	37.8	378	0.4998	0.7147	0.4998	0.7069
No log	38.0	380	0.4980	0.6997	0.4980	0.7057
No log	38.2	382	0.5043	0.6852	0.5043	0.7102
No log	38.4	384	0.4979	0.6852	0.4979	0.7056
No log	38.6	386	0.4827	0.7069	0.4827	0.6948
No log	38.8	388	0.4913	0.6706	0.4913	0.7010
No log	39.0	390	0.5108	0.6221	0.5108	0.7147
No log	39.2	392	0.5180	0.6143	0.5180	0.7197
No log	39.4	394	0.4845	0.6387	0.4845	0.6961
No log	39.6	396	0.4539	0.6743	0.4539	0.6737
No log	39.8	398	0.4584	0.6847	0.4584	0.6771
No log	40.0	400	0.4623	0.6847	0.4623	0.6799
No log	40.2	402	0.4565	0.6847	0.4565	0.6757
No log	40.4	404	0.4503	0.6735	0.4503	0.6711
No log	40.6	406	0.4810	0.6477	0.4810	0.6936
No log	40.8	408	0.5031	0.7082	0.5031	0.7093
No log	41.0	410	0.5100	0.7082	0.5100	0.7142
No log	41.2	412	0.5132	0.6874	0.5132	0.7164
No log	41.4	414	0.5189	0.6694	0.5189	0.7204
No log	41.6	416	0.5284	0.7006	0.5284	0.7269
No log	41.8	418	0.5135	0.6700	0.5135	0.7166
No log	42.0	420	0.4937	0.7067	0.4937	0.7026
No log	42.2	422	0.4870	0.6988	0.4870	0.6978
No log	42.4	424	0.4866	0.6570	0.4866	0.6975
No log	42.6	426	0.4868	0.6721	0.4868	0.6977
No log	42.8	428	0.4908	0.6879	0.4908	0.7005
No log	43.0	430	0.4982	0.6730	0.4982	0.7058
No log	43.2	432	0.4986	0.6888	0.4986	0.7061
No log	43.4	434	0.4965	0.6888	0.4965	0.7046
No log	43.6	436	0.4856	0.6730	0.4856	0.6968
No log	43.8	438	0.4767	0.6847	0.4767	0.6905
No log	44.0	440	0.4786	0.6860	0.4786	0.6918
No log	44.2	442	0.4740	0.6860	0.4740	0.6885
No log	44.4	444	0.4712	0.6745	0.4712	0.6865
No log	44.6	446	0.4770	0.6243	0.4770	0.6906
No log	44.8	448	0.4815	0.6073	0.4815	0.6939
No log	45.0	450	0.4827	0.5900	0.4827	0.6948
No log	45.2	452	0.4901	0.5786	0.4901	0.7001
No log	45.4	454	0.4839	0.5786	0.4839	0.6956
No log	45.6	456	0.4738	0.5899	0.4738	0.6883
No log	45.8	458	0.4747	0.6046	0.4747	0.6890
No log	46.0	460	0.4798	0.5860	0.4798	0.6927
No log	46.2	462	0.4789	0.6650	0.4789	0.6921
No log	46.4	464	0.4916	0.6815	0.4916	0.7012
No log	46.6	466	0.5150	0.6586	0.5150	0.7176
No log	46.8	468	0.5440	0.6246	0.5440	0.7375
No log	47.0	470	0.5578	0.6256	0.5578	0.7469
No log	47.2	472	0.5640	0.6544	0.5640	0.7510
No log	47.4	474	0.5774	0.6485	0.5774	0.7598
No log	47.6	476	0.5634	0.6568	0.5634	0.7506
No log	47.8	478	0.5293	0.6547	0.5293	0.7276
No log	48.0	480	0.4990	0.6783	0.4990	0.7064
No log	48.2	482	0.4870	0.6667	0.4870	0.6979
No log	48.4	484	0.4864	0.6569	0.4864	0.6975
No log	48.6	486	0.4933	0.6253	0.4933	0.7024
No log	48.8	488	0.4965	0.6152	0.4965	0.7046
No log	49.0	490	0.4904	0.6322	0.4904	0.7003
No log	49.2	492	0.4851	0.6569	0.4851	0.6965
No log	49.4	494	0.4926	0.6730	0.4926	0.7019
No log	49.6	496	0.4958	0.6253	0.4958	0.7041
No log	49.8	498	0.4932	0.6084	0.4932	0.7023
0.2885	50.0	500	0.4845	0.6569	0.4845	0.6961
0.2885	50.2	502	0.4785	0.6574	0.4785	0.6917
0.2885	50.4	504	0.4692	0.6751	0.4692	0.6850
0.2885	50.6	506	0.4684	0.6751	0.4684	0.6844
0.2885	50.8	508	0.4683	0.6171	0.4683	0.6843
0.2885	51.0	510	0.4798	0.6199	0.4798	0.6927
0.2885	51.2	512	0.5000	0.6282	0.5000	0.7071
0.2885	51.4	514	0.5157	0.6092	0.5157	0.7181
0.2885	51.6	516	0.5124	0.5920	0.5124	0.7158

Framework versions

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