ArabicNewSplits6_FineTuningAraBERT_run2_AugV5_k9_task2_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: 0.7000
• Qwk: 0.5282
• Mse: 0.7000
• Rmse: 0.8367

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	0.0435	2	4.1455	-0.0116	4.1455	2.0361
No log	0.0870	4	2.0507	0.0303	2.0507	1.4320
No log	0.1304	6	1.5264	0.0380	1.5264	1.2355
No log	0.1739	8	1.2385	-0.0621	1.2385	1.1129
No log	0.2174	10	1.5037	-0.0840	1.5037	1.2262
No log	0.2609	12	1.0924	-0.0865	1.0924	1.0452
No log	0.3043	14	0.8127	0.1137	0.8127	0.9015
No log	0.3478	16	0.7836	0.2036	0.7836	0.8852
No log	0.3913	18	0.7948	0.1649	0.7948	0.8915
No log	0.4348	20	0.8660	-0.0332	0.8660	0.9306
No log	0.4783	22	0.7451	0.1581	0.7451	0.8632
No log	0.5217	24	0.6445	0.4014	0.6445	0.8028
No log	0.5652	26	0.6563	0.3030	0.6563	0.8101
No log	0.6087	28	0.6909	0.3296	0.6909	0.8312
No log	0.6522	30	0.7943	0.3409	0.7943	0.8912
No log	0.6957	32	1.0544	0.2358	1.0544	1.0268
No log	0.7391	34	1.3649	0.2011	1.3649	1.1683
No log	0.7826	36	1.3786	0.1919	1.3786	1.1741
No log	0.8261	38	1.0267	0.2485	1.0267	1.0133
No log	0.8696	40	0.7903	0.3307	0.7903	0.8890
No log	0.9130	42	0.6885	0.2705	0.6885	0.8298
No log	0.9565	44	0.6692	0.2253	0.6692	0.8180
No log	1.0	46	0.6556	0.2414	0.6556	0.8097
No log	1.0435	48	0.6214	0.2993	0.6214	0.7883
No log	1.0870	50	0.6135	0.4113	0.6135	0.7833
No log	1.1304	52	0.6837	0.4163	0.6837	0.8269
No log	1.1739	54	0.6829	0.4524	0.6829	0.8264
No log	1.2174	56	0.6958	0.3875	0.6958	0.8342
No log	1.2609	58	0.7871	0.3739	0.7871	0.8872
No log	1.3043	60	0.8043	0.3533	0.8043	0.8968
No log	1.3478	62	0.8804	0.3445	0.8804	0.9383
No log	1.3913	64	0.7655	0.3865	0.7655	0.8749
No log	1.4348	66	0.7804	0.3897	0.7804	0.8834
No log	1.4783	68	0.6667	0.4381	0.6667	0.8165
No log	1.5217	70	0.6017	0.4941	0.6017	0.7757
No log	1.5652	72	0.6392	0.4976	0.6392	0.7995
No log	1.6087	74	0.5816	0.4754	0.5816	0.7626
No log	1.6522	76	0.6021	0.4263	0.6021	0.7759
No log	1.6957	78	0.6125	0.4288	0.6125	0.7826
No log	1.7391	80	0.6516	0.4339	0.6516	0.8072
No log	1.7826	82	0.6457	0.4381	0.6457	0.8035
No log	1.8261	84	0.6445	0.4447	0.6445	0.8028
No log	1.8696	86	0.6282	0.4568	0.6282	0.7926
No log	1.9130	88	0.6613	0.4558	0.6613	0.8132
No log	1.9565	90	0.9430	0.3407	0.9430	0.9711
No log	2.0	92	1.2345	0.2551	1.2345	1.1111
No log	2.0435	94	1.1224	0.2854	1.1224	1.0594
No log	2.0870	96	0.8062	0.3115	0.8062	0.8979
No log	2.1304	98	0.5801	0.4212	0.5801	0.7617
No log	2.1739	100	0.5333	0.5393	0.5333	0.7303
No log	2.2174	102	0.5693	0.4575	0.5693	0.7545
No log	2.2609	104	0.6065	0.4683	0.6065	0.7788
No log	2.3043	106	0.6225	0.5062	0.6225	0.7890
No log	2.3478	108	0.6191	0.4441	0.6191	0.7868
No log	2.3913	110	0.6257	0.4738	0.6257	0.7910
No log	2.4348	112	0.7032	0.4959	0.7032	0.8386
No log	2.4783	114	0.7741	0.5057	0.7741	0.8798
No log	2.5217	116	0.7386	0.4690	0.7386	0.8594
No log	2.5652	118	0.6689	0.5031	0.6689	0.8179
No log	2.6087	120	0.6751	0.4829	0.6751	0.8216
No log	2.6522	122	0.7733	0.5045	0.7733	0.8794
No log	2.6957	124	1.0752	0.3871	1.0752	1.0369
No log	2.7391	126	1.0640	0.3797	1.0640	1.0315
No log	2.7826	128	0.7966	0.5120	0.7966	0.8925
No log	2.8261	130	0.6896	0.5269	0.6896	0.8305
No log	2.8696	132	0.7242	0.5152	0.7242	0.8510
No log	2.9130	134	0.6736	0.5050	0.6736	0.8208
No log	2.9565	136	0.6418	0.5388	0.6418	0.8011
No log	3.0	138	0.6424	0.5294	0.6424	0.8015
No log	3.0435	140	0.6495	0.5264	0.6495	0.8059
No log	3.0870	142	0.6760	0.4613	0.6760	0.8222
No log	3.1304	144	0.6685	0.4655	0.6685	0.8176
No log	3.1739	146	0.6347	0.5358	0.6347	0.7967
No log	3.2174	148	0.6523	0.5419	0.6523	0.8076
No log	3.2609	150	0.6328	0.5627	0.6328	0.7955
No log	3.3043	152	0.7093	0.4099	0.7093	0.8422
No log	3.3478	154	0.7920	0.3883	0.7920	0.8899
No log	3.3913	156	0.7489	0.4284	0.7489	0.8654
No log	3.4348	158	0.6639	0.5374	0.6639	0.8148
No log	3.4783	160	0.6655	0.5141	0.6655	0.8158
No log	3.5217	162	0.7220	0.4041	0.7220	0.8497
No log	3.5652	164	0.7317	0.4285	0.7317	0.8554
No log	3.6087	166	0.6763	0.5100	0.6763	0.8224
No log	3.6522	168	0.6804	0.5176	0.6804	0.8249
No log	3.6957	170	0.7434	0.4977	0.7434	0.8622
No log	3.7391	172	0.7632	0.4739	0.7632	0.8736
No log	3.7826	174	0.7252	0.5108	0.7252	0.8516
No log	3.8261	176	0.6938	0.4988	0.6938	0.8330
No log	3.8696	178	0.7061	0.5095	0.7061	0.8403
No log	3.9130	180	0.7938	0.4874	0.7938	0.8909
No log	3.9565	182	0.8921	0.4804	0.8921	0.9445
No log	4.0	184	0.8947	0.4885	0.8947	0.9459
No log	4.0435	186	0.7927	0.5031	0.7927	0.8904
No log	4.0870	188	0.7758	0.5023	0.7758	0.8808
No log	4.1304	190	0.7628	0.5023	0.7628	0.8734
No log	4.1739	192	0.8057	0.5130	0.8057	0.8976
No log	4.2174	194	0.7829	0.5325	0.7829	0.8848
No log	4.2609	196	0.6931	0.4973	0.6931	0.8325
No log	4.3043	198	0.6825	0.4897	0.6825	0.8262
No log	4.3478	200	0.7006	0.5045	0.7006	0.8370
No log	4.3913	202	0.7290	0.5069	0.7290	0.8538
No log	4.4348	204	0.7668	0.5016	0.7668	0.8757
No log	4.4783	206	0.8170	0.5119	0.8170	0.9039
No log	4.5217	208	0.8210	0.4899	0.8210	0.9061
No log	4.5652	210	0.8071	0.5108	0.8071	0.8984
No log	4.6087	212	0.7879	0.4963	0.7879	0.8876
No log	4.6522	214	0.7757	0.5182	0.7757	0.8807
No log	4.6957	216	0.7448	0.4896	0.7448	0.8630
No log	4.7391	218	0.7559	0.5101	0.7559	0.8694
No log	4.7826	220	0.7514	0.5147	0.7514	0.8668
No log	4.8261	222	0.7495	0.4827	0.7495	0.8657
No log	4.8696	224	0.7542	0.4827	0.7542	0.8685
No log	4.9130	226	0.7301	0.4978	0.7301	0.8545
No log	4.9565	228	0.7082	0.4936	0.7082	0.8416
No log	5.0	230	0.6921	0.5205	0.6921	0.8319
No log	5.0435	232	0.6656	0.4990	0.6656	0.8159
No log	5.0870	234	0.6706	0.5041	0.6706	0.8189
No log	5.1304	236	0.7702	0.4273	0.7702	0.8776
No log	5.1739	238	0.9294	0.4590	0.9294	0.9641
No log	5.2174	240	0.9075	0.4739	0.9075	0.9526
No log	5.2609	242	0.8258	0.4399	0.8258	0.9088
No log	5.3043	244	0.7559	0.4901	0.7559	0.8695
No log	5.3478	246	0.7441	0.5148	0.7441	0.8626
No log	5.3913	248	0.7774	0.4901	0.7774	0.8817
No log	5.4348	250	0.8681	0.4778	0.8681	0.9317
No log	5.4783	252	0.9110	0.4515	0.9110	0.9545
No log	5.5217	254	0.8130	0.4675	0.8130	0.9017
No log	5.5652	256	0.7262	0.494	0.7262	0.8522
No log	5.6087	258	0.7290	0.4905	0.7290	0.8538
No log	5.6522	260	0.7299	0.5058	0.7299	0.8543
No log	5.6957	262	0.7298	0.5070	0.7298	0.8543
No log	5.7391	264	0.7191	0.5119	0.7191	0.8480
No log	5.7826	266	0.6973	0.4969	0.6973	0.8350
No log	5.8261	268	0.6996	0.5211	0.6996	0.8364
No log	5.8696	270	0.6862	0.5228	0.6862	0.8284
No log	5.9130	272	0.6740	0.4837	0.6740	0.8210
No log	5.9565	274	0.7058	0.4767	0.7058	0.8401
No log	6.0	276	0.7452	0.5011	0.7452	0.8632
No log	6.0435	278	0.7386	0.5011	0.7386	0.8594
No log	6.0870	280	0.7565	0.5011	0.7565	0.8698
No log	6.1304	282	0.7701	0.5163	0.7701	0.8775
No log	6.1739	284	0.7577	0.4956	0.7577	0.8705
No log	6.2174	286	0.7500	0.5128	0.7500	0.8660
No log	6.2609	288	0.7512	0.4843	0.7512	0.8667
No log	6.3043	290	0.7577	0.4799	0.7577	0.8705
No log	6.3478	292	0.7713	0.4799	0.7713	0.8782
No log	6.3913	294	0.7793	0.4918	0.7793	0.8828
No log	6.4348	296	0.7562	0.5153	0.7562	0.8696
No log	6.4783	298	0.7314	0.5196	0.7314	0.8552
No log	6.5217	300	0.7533	0.5085	0.7533	0.8679
No log	6.5652	302	0.7596	0.5228	0.7596	0.8716
No log	6.6087	304	0.7612	0.5058	0.7612	0.8725
No log	6.6522	306	0.7718	0.5168	0.7718	0.8785
No log	6.6957	308	0.7999	0.4927	0.7999	0.8943
No log	6.7391	310	0.7747	0.4942	0.7747	0.8802
No log	6.7826	312	0.7303	0.5027	0.7303	0.8545
No log	6.8261	314	0.6715	0.5249	0.6715	0.8194
No log	6.8696	316	0.6416	0.4960	0.6416	0.8010
No log	6.9130	318	0.6393	0.4952	0.6393	0.7995
No log	6.9565	320	0.6560	0.4985	0.6560	0.8099
No log	7.0	322	0.6780	0.5126	0.6780	0.8234
No log	7.0435	324	0.7063	0.5388	0.7063	0.8404
No log	7.0870	326	0.7466	0.4971	0.7466	0.8641
No log	7.1304	328	0.7970	0.4904	0.7970	0.8927
No log	7.1739	330	0.7900	0.4904	0.7900	0.8888
No log	7.2174	332	0.7417	0.5293	0.7417	0.8612
No log	7.2609	334	0.7197	0.5163	0.7197	0.8483
No log	7.3043	336	0.7076	0.5216	0.7076	0.8412
No log	7.3478	338	0.6890	0.5237	0.6890	0.8300
No log	7.3913	340	0.6842	0.5148	0.6842	0.8271
No log	7.4348	342	0.6721	0.5158	0.6721	0.8198
No log	7.4783	344	0.6722	0.5369	0.6722	0.8199
No log	7.5217	346	0.6739	0.5256	0.6739	0.8209
No log	7.5652	348	0.6706	0.5471	0.6706	0.8189
No log	7.6087	350	0.6654	0.5337	0.6654	0.8157
No log	7.6522	352	0.6735	0.5369	0.6735	0.8207
No log	7.6957	354	0.6814	0.5353	0.6814	0.8254
No log	7.7391	356	0.6836	0.5455	0.6836	0.8268
No log	7.7826	358	0.6824	0.5068	0.6824	0.8261
No log	7.8261	360	0.6880	0.4964	0.6880	0.8295
No log	7.8696	362	0.6950	0.4964	0.6950	0.8337
No log	7.9130	364	0.7035	0.4964	0.7035	0.8387
No log	7.9565	366	0.7167	0.4952	0.7167	0.8466
No log	8.0	368	0.7343	0.5016	0.7343	0.8569
No log	8.0435	370	0.7505	0.5125	0.7505	0.8663
No log	8.0870	372	0.7387	0.5118	0.7387	0.8595
No log	8.1304	374	0.7043	0.4804	0.7043	0.8392
No log	8.1739	376	0.6734	0.4917	0.6734	0.8206
No log	8.2174	378	0.6595	0.5202	0.6595	0.8121
No log	8.2609	380	0.6669	0.5087	0.6669	0.8166
No log	8.3043	382	0.6706	0.4852	0.6706	0.8189
No log	8.3478	384	0.6589	0.4934	0.6589	0.8117
No log	8.3913	386	0.6422	0.5196	0.6422	0.8014
No log	8.4348	388	0.6377	0.4897	0.6377	0.7986
No log	8.4783	390	0.6489	0.5014	0.6489	0.8056
No log	8.5217	392	0.6693	0.4901	0.6693	0.8181
No log	8.5652	394	0.6854	0.4977	0.6854	0.8279
No log	8.6087	396	0.6883	0.4896	0.6883	0.8297
No log	8.6522	398	0.6858	0.5158	0.6858	0.8282
No log	8.6957	400	0.6968	0.5278	0.6968	0.8348
No log	8.7391	402	0.6985	0.5144	0.6985	0.8358
No log	8.7826	404	0.6967	0.5052	0.6967	0.8347
No log	8.8261	406	0.6990	0.4981	0.6990	0.8361
No log	8.8696	408	0.7017	0.5122	0.7017	0.8377
No log	8.9130	410	0.7083	0.5144	0.7083	0.8416
No log	8.9565	412	0.7148	0.4878	0.7148	0.8455
No log	9.0	414	0.7191	0.4878	0.7191	0.8480
No log	9.0435	416	0.7112	0.4878	0.7112	0.8433
No log	9.0870	418	0.7012	0.5278	0.7012	0.8374
No log	9.1304	420	0.6900	0.5198	0.6900	0.8307
No log	9.1739	422	0.6825	0.5122	0.6825	0.8261
No log	9.2174	424	0.6818	0.4972	0.6818	0.8257
No log	9.2609	426	0.6827	0.4972	0.6827	0.8262
No log	9.3043	428	0.6817	0.4989	0.6817	0.8257
No log	9.3478	430	0.6820	0.4989	0.6820	0.8258
No log	9.3913	432	0.6847	0.5122	0.6847	0.8275
No log	9.4348	434	0.6865	0.5122	0.6865	0.8286
No log	9.4783	436	0.6867	0.5122	0.6867	0.8287
No log	9.5217	438	0.6883	0.5122	0.6883	0.8296
No log	9.5652	440	0.6898	0.5177	0.6898	0.8305
No log	9.6087	442	0.6926	0.5122	0.6926	0.8322
No log	9.6522	444	0.6946	0.5122	0.6946	0.8334
No log	9.6957	446	0.6962	0.5129	0.6962	0.8344
No log	9.7391	448	0.6982	0.5256	0.6982	0.8356
No log	9.7826	450	0.6990	0.5203	0.6990	0.8360
No log	9.8261	452	0.7002	0.5336	0.7002	0.8368
No log	9.8696	454	0.7003	0.5336	0.7003	0.8369
No log	9.9130	456	0.7003	0.5282	0.7003	0.8368
No log	9.9565	458	0.6999	0.5282	0.6999	0.8366
No log	10.0	460	0.7000	0.5282	0.7000	0.8367

Framework versions

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