ArabicNewSplits6_FineTuningAraBERT_run3_AugV5_k8_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: 0.7806
• Qwk: 0.4914
• Mse: 0.7806
• Rmse: 0.8835

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	0.0476	2	4.0706	-0.0134	4.0706	2.0176
No log	0.0952	4	2.0241	0.0553	2.0241	1.4227
No log	0.1429	6	1.2067	0.0495	1.2067	1.0985
No log	0.1905	8	0.9508	0.0109	0.9508	0.9751
No log	0.2381	10	0.8303	-0.1110	0.8303	0.9112
No log	0.2857	12	0.7530	0.1308	0.7530	0.8677
No log	0.3333	14	0.7443	0.2111	0.7443	0.8628
No log	0.3810	16	0.7696	0.1481	0.7696	0.8773
No log	0.4286	18	0.8110	0.0986	0.8110	0.9006
No log	0.4762	20	1.0374	0.0650	1.0374	1.0185
No log	0.5238	22	0.9514	0.0846	0.9514	0.9754
No log	0.5714	24	0.8356	0.1230	0.8356	0.9141
No log	0.6190	26	0.8553	0.0104	0.8553	0.9248
No log	0.6667	28	0.8154	0.0513	0.8154	0.9030
No log	0.7143	30	0.7208	0.2703	0.7208	0.8490
No log	0.7619	32	0.6805	0.3333	0.6805	0.8249
No log	0.8095	34	0.6541	0.4014	0.6541	0.8088
No log	0.8571	36	0.6308	0.4014	0.6308	0.7942
No log	0.9048	38	0.6188	0.4103	0.6188	0.7867
No log	0.9524	40	0.6632	0.3114	0.6632	0.8144
No log	1.0	42	0.7985	0.1643	0.7985	0.8936
No log	1.0476	44	0.8438	0.1619	0.8438	0.9186
No log	1.0952	46	0.7392	0.2212	0.7392	0.8598
No log	1.1429	48	0.6110	0.3812	0.6110	0.7817
No log	1.1905	50	0.5889	0.3376	0.5889	0.7674
No log	1.2381	52	0.5814	0.3429	0.5814	0.7625
No log	1.2857	54	0.6053	0.4255	0.6053	0.7780
No log	1.3333	56	0.7971	0.2304	0.7971	0.8928
No log	1.3810	58	0.9881	0.2745	0.9881	0.9940
No log	1.4286	60	0.7330	0.3902	0.7330	0.8561
No log	1.4762	62	0.6210	0.4524	0.6210	0.7880
No log	1.5238	64	0.5963	0.3942	0.5963	0.7722
No log	1.5714	66	0.5710	0.4497	0.5710	0.7556
No log	1.6190	68	0.7579	0.4072	0.7579	0.8706
No log	1.6667	70	1.2585	0.2297	1.2585	1.1218
No log	1.7143	72	1.2057	0.2437	1.2057	1.0980
No log	1.7619	74	0.8620	0.2706	0.8620	0.9284
No log	1.8095	76	0.6069	0.4587	0.6069	0.7791
No log	1.8571	78	0.6274	0.4404	0.6274	0.7921
No log	1.9048	80	0.6594	0.3586	0.6594	0.8120
No log	1.9524	82	0.6053	0.4215	0.6053	0.7780
No log	2.0	84	0.5714	0.4276	0.5714	0.7559
No log	2.0476	86	0.5509	0.4573	0.5509	0.7422
No log	2.0952	88	0.5681	0.5061	0.5681	0.7537
No log	2.1429	90	0.5534	0.5444	0.5534	0.7439
No log	2.1905	92	0.5384	0.4768	0.5384	0.7338
No log	2.2381	94	0.5401	0.5362	0.5401	0.7349
No log	2.2857	96	0.5478	0.5327	0.5478	0.7401
No log	2.3333	98	0.5671	0.5711	0.5671	0.7530
No log	2.3810	100	0.6304	0.5286	0.6304	0.7940
No log	2.4286	102	0.8515	0.2821	0.8515	0.9228
No log	2.4762	104	0.9739	0.3294	0.9739	0.9868
No log	2.5238	106	0.8237	0.3173	0.8237	0.9076
No log	2.5714	108	0.6541	0.5161	0.6541	0.8088
No log	2.6190	110	0.6141	0.4769	0.6141	0.7836
No log	2.6667	112	0.6166	0.4434	0.6166	0.7853
No log	2.7143	114	0.6152	0.4902	0.6152	0.7844
No log	2.7619	116	0.6599	0.5230	0.6599	0.8123
No log	2.8095	118	0.6782	0.5161	0.6782	0.8235
No log	2.8571	120	0.7136	0.4926	0.7136	0.8447
No log	2.9048	122	0.7243	0.4739	0.7243	0.8511
No log	2.9524	124	0.7122	0.4916	0.7122	0.8439
No log	3.0	126	0.6897	0.4846	0.6897	0.8305
No log	3.0476	128	0.6395	0.5099	0.6395	0.7997
No log	3.0952	130	0.6463	0.4915	0.6464	0.8040
No log	3.1429	132	0.6605	0.5133	0.6605	0.8127
No log	3.1905	134	0.6987	0.5093	0.6987	0.8359
No log	3.2381	136	0.7351	0.4614	0.7351	0.8574
No log	3.2857	138	0.7307	0.4782	0.7307	0.8548
No log	3.3333	140	0.7123	0.5403	0.7123	0.8440
No log	3.3810	142	0.8285	0.4716	0.8285	0.9102
No log	3.4286	144	0.8713	0.4461	0.8713	0.9334
No log	3.4762	146	0.7513	0.4913	0.7513	0.8668
No log	3.5238	148	0.7007	0.4895	0.7007	0.8371
No log	3.5714	150	0.7611	0.4868	0.7611	0.8724
No log	3.6190	152	0.7745	0.4724	0.7745	0.8801
No log	3.6667	154	0.7985	0.4563	0.7985	0.8936
No log	3.7143	156	0.6983	0.4974	0.6983	0.8357
No log	3.7619	158	0.6561	0.4715	0.6561	0.8100
No log	3.8095	160	0.6593	0.4789	0.6593	0.8120
No log	3.8571	162	0.6589	0.4897	0.6589	0.8117
No log	3.9048	164	0.6753	0.4732	0.6753	0.8218
No log	3.9524	166	0.7307	0.4855	0.7307	0.8548
No log	4.0	168	0.7339	0.4625	0.7339	0.8567
No log	4.0476	170	0.7079	0.4694	0.7079	0.8414
No log	4.0952	172	0.7158	0.4927	0.7158	0.8460
No log	4.1429	174	0.7532	0.4864	0.7532	0.8678
No log	4.1905	176	0.7513	0.4864	0.7513	0.8668
No log	4.2381	178	0.7452	0.4938	0.7452	0.8632
No log	4.2857	180	0.7195	0.4871	0.7195	0.8482
No log	4.3333	182	0.7017	0.4985	0.7017	0.8377
No log	4.3810	184	0.7053	0.4862	0.7053	0.8398
No log	4.4286	186	0.7140	0.4869	0.7140	0.8450
No log	4.4762	188	0.7129	0.4869	0.7129	0.8443
No log	4.5238	190	0.7482	0.4552	0.7482	0.8650
No log	4.5714	192	0.8490	0.3804	0.8490	0.9214
No log	4.6190	194	0.9307	0.3951	0.9307	0.9647
No log	4.6667	196	0.8894	0.3990	0.8894	0.9431
No log	4.7143	198	0.8130	0.4400	0.8130	0.9017
No log	4.7619	200	0.7854	0.4634	0.7854	0.8862
No log	4.8095	202	0.7738	0.4773	0.7738	0.8797
No log	4.8571	204	0.7731	0.4829	0.7731	0.8792
No log	4.9048	206	0.7660	0.4822	0.7660	0.8752
No log	4.9524	208	0.7717	0.4795	0.7717	0.8785
No log	5.0	210	0.8411	0.4404	0.8411	0.9171
No log	5.0476	212	0.8941	0.4267	0.8941	0.9456
No log	5.0952	214	0.8675	0.4404	0.8675	0.9314
No log	5.1429	216	0.8368	0.4281	0.8368	0.9148
No log	5.1905	218	0.8261	0.4066	0.8261	0.9089
No log	5.2381	220	0.8153	0.4372	0.8153	0.9029
No log	5.2857	222	0.8091	0.4864	0.8091	0.8995
No log	5.3333	224	0.8031	0.4584	0.8031	0.8962
No log	5.3810	226	0.8015	0.4247	0.8015	0.8953
No log	5.4286	228	0.8080	0.4192	0.8080	0.8989
No log	5.4762	230	0.8107	0.4250	0.8107	0.9004
No log	5.5238	232	0.7707	0.4572	0.7707	0.8779
No log	5.5714	234	0.7232	0.4841	0.7232	0.8504
No log	5.6190	236	0.7182	0.4959	0.7182	0.8475
No log	5.6667	238	0.7378	0.4788	0.7378	0.8590
No log	5.7143	240	0.7403	0.4899	0.7403	0.8604
No log	5.7619	242	0.7492	0.4877	0.7492	0.8656
No log	5.8095	244	0.7381	0.4920	0.7381	0.8592
No log	5.8571	246	0.7264	0.5082	0.7264	0.8523
No log	5.9048	248	0.7276	0.5072	0.7276	0.8530
No log	5.9524	250	0.7442	0.4934	0.7442	0.8627
No log	6.0	252	0.7587	0.5039	0.7587	0.8710
No log	6.0476	254	0.7537	0.5030	0.7537	0.8681
No log	6.0952	256	0.7499	0.4795	0.7499	0.8660
No log	6.1429	258	0.7422	0.5397	0.7422	0.8615
No log	6.1905	260	0.7526	0.4591	0.7526	0.8675
No log	6.2381	262	0.7981	0.4564	0.7981	0.8934
No log	6.2857	264	0.8128	0.4453	0.8128	0.9016
No log	6.3333	266	0.7845	0.4799	0.7845	0.8857
No log	6.3810	268	0.7750	0.4654	0.7750	0.8803
No log	6.4286	270	0.7799	0.4988	0.7799	0.8831
No log	6.4762	272	0.7976	0.4782	0.7976	0.8931
No log	6.5238	274	0.8345	0.4469	0.8345	0.9135
No log	6.5714	276	0.8494	0.4415	0.8494	0.9216
No log	6.6190	278	0.8529	0.4361	0.8529	0.9235
No log	6.6667	280	0.8260	0.4609	0.8260	0.9088
No log	6.7143	282	0.8058	0.4757	0.8058	0.8977
No log	6.7619	284	0.7981	0.4698	0.7981	0.8934
No log	6.8095	286	0.7977	0.4575	0.7977	0.8931
No log	6.8571	288	0.7906	0.4698	0.7906	0.8892
No log	6.9048	290	0.7938	0.4698	0.7938	0.8909
No log	6.9524	292	0.8079	0.4382	0.8079	0.8988
No log	7.0	294	0.8074	0.4575	0.8074	0.8986
No log	7.0476	296	0.8013	0.4997	0.8013	0.8951
No log	7.0952	298	0.8026	0.4934	0.8026	0.8959
No log	7.1429	300	0.8077	0.4558	0.8077	0.8987
No log	7.1905	302	0.8075	0.4994	0.8075	0.8986
No log	7.2381	304	0.8246	0.4913	0.8246	0.9081
No log	7.2857	306	0.8402	0.4533	0.8402	0.9166
No log	7.3333	308	0.8630	0.4547	0.8630	0.9290
No log	7.3810	310	0.8481	0.4533	0.8481	0.9209
No log	7.4286	312	0.8083	0.4942	0.8083	0.8991
No log	7.4762	314	0.7806	0.4827	0.7806	0.8835
No log	7.5238	316	0.7765	0.5006	0.7765	0.8812
No log	7.5714	318	0.7704	0.5006	0.7704	0.8777
No log	7.6190	320	0.7517	0.4892	0.7517	0.8670
No log	7.6667	322	0.7404	0.5003	0.7404	0.8605
No log	7.7143	324	0.7580	0.5047	0.7580	0.8706
No log	7.7619	326	0.7696	0.5122	0.7696	0.8772
No log	7.8095	328	0.7774	0.5064	0.7774	0.8817
No log	7.8571	330	0.7806	0.5112	0.7806	0.8835
No log	7.9048	332	0.7892	0.5112	0.7892	0.8884
No log	7.9524	334	0.8044	0.4890	0.8044	0.8969
No log	8.0	336	0.8271	0.4615	0.8271	0.9095
No log	8.0476	338	0.8298	0.4696	0.8298	0.9110
No log	8.0952	340	0.8139	0.4615	0.8139	0.9022
No log	8.1429	342	0.7970	0.5256	0.7970	0.8927
No log	8.1905	344	0.7968	0.5034	0.7968	0.8926
No log	8.2381	346	0.7944	0.5034	0.7944	0.8913
No log	8.2857	348	0.7869	0.4986	0.7869	0.8871
No log	8.3333	350	0.7757	0.5076	0.7757	0.8808
No log	8.3810	352	0.7689	0.4873	0.7689	0.8769
No log	8.4286	354	0.7614	0.4986	0.7614	0.8726
No log	8.4762	356	0.7526	0.5017	0.7526	0.8675
No log	8.5238	358	0.7465	0.5137	0.7465	0.8640
No log	8.5714	360	0.7427	0.5102	0.7427	0.8618
No log	8.6190	362	0.7429	0.5044	0.7429	0.8619
No log	8.6667	364	0.7460	0.5200	0.7460	0.8637
No log	8.7143	366	0.7474	0.5044	0.7474	0.8645
No log	8.7619	368	0.7511	0.5140	0.7511	0.8667
No log	8.8095	370	0.7629	0.5211	0.7629	0.8735
No log	8.8571	372	0.7782	0.5211	0.7782	0.8821
No log	8.9048	374	0.7856	0.5211	0.7856	0.8864
No log	8.9524	376	0.7903	0.5211	0.7903	0.8890
No log	9.0	378	0.7914	0.5211	0.7914	0.8896
No log	9.0476	380	0.7954	0.4812	0.7954	0.8918
No log	9.0952	382	0.7987	0.4897	0.7987	0.8937
No log	9.1429	384	0.8013	0.4914	0.8013	0.8952
No log	9.1905	386	0.8022	0.5123	0.8022	0.8957
No log	9.2381	388	0.8023	0.5123	0.8023	0.8957
No log	9.2857	390	0.8010	0.4914	0.8010	0.8950
No log	9.3333	392	0.8005	0.4907	0.8005	0.8947
No log	9.3810	394	0.8003	0.4819	0.8003	0.8946
No log	9.4286	396	0.7993	0.5046	0.7993	0.8940
No log	9.4762	398	0.7986	0.5216	0.7986	0.8937
No log	9.5238	400	0.7975	0.5083	0.7975	0.8930
No log	9.5714	402	0.7950	0.5083	0.7950	0.8916
No log	9.6190	404	0.7913	0.5216	0.7913	0.8896
No log	9.6667	406	0.7886	0.5216	0.7886	0.8880
No log	9.7143	408	0.7864	0.5110	0.7864	0.8868
No log	9.7619	410	0.7842	0.4928	0.7842	0.8856
No log	9.8095	412	0.7830	0.4873	0.7830	0.8849
No log	9.8571	414	0.7819	0.4953	0.7819	0.8842
No log	9.9048	416	0.7812	0.4914	0.7812	0.8838
No log	9.9524	418	0.7807	0.4914	0.7807	0.8836
No log	10.0	420	0.7806	0.4914	0.7806	0.8835

Framework versions

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