ArabicNewSplits6_FineTuningAraBERT_run3_AugV5_k8_task1_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: 0.7566
• Qwk: 0.7016
• Mse: 0.7566
• Rmse: 0.8698

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	5.0529	-0.0195	5.0529	2.2479
No log	0.0952	4	3.0146	0.0892	3.0146	1.7362
No log	0.1429	6	1.8552	0.0971	1.8552	1.3621
No log	0.1905	8	1.5226	0.0075	1.5226	1.2339
No log	0.2381	10	1.3328	0.1398	1.3328	1.1545
No log	0.2857	12	1.2518	0.1355	1.2518	1.1188
No log	0.3333	14	1.2768	0.1596	1.2768	1.1299
No log	0.3810	16	1.2107	0.2872	1.2107	1.1003
No log	0.4286	18	1.1811	0.2872	1.1811	1.0868
No log	0.4762	20	1.1244	0.3164	1.1244	1.0604
No log	0.5238	22	1.1616	0.2881	1.1616	1.0778
No log	0.5714	24	1.4568	0.3280	1.4568	1.2070
No log	0.6190	26	1.9124	0.2225	1.9124	1.3829
No log	0.6667	28	1.5412	0.2937	1.5412	1.2415
No log	0.7143	30	1.1686	0.4357	1.1686	1.0810
No log	0.7619	32	1.0642	0.4994	1.0642	1.0316
No log	0.8095	34	0.9920	0.4555	0.9920	0.9960
No log	0.8571	36	0.9968	0.4026	0.9968	0.9984
No log	0.9048	38	0.9253	0.3937	0.9253	0.9619
No log	0.9524	40	0.8545	0.4728	0.8545	0.9244
No log	1.0	42	1.1777	0.4491	1.1777	1.0852
No log	1.0476	44	1.7743	0.2890	1.7743	1.3320
No log	1.0952	46	1.6723	0.3505	1.6723	1.2932
No log	1.1429	48	1.1185	0.4933	1.1185	1.0576
No log	1.1905	50	0.8938	0.5772	0.8938	0.9454
No log	1.2381	52	0.9096	0.5609	0.9096	0.9537
No log	1.2857	54	1.0923	0.4951	1.0923	1.0451
No log	1.3333	56	1.4484	0.4071	1.4484	1.2035
No log	1.3810	58	1.6729	0.3901	1.6729	1.2934
No log	1.4286	60	1.4145	0.4807	1.4145	1.1893
No log	1.4762	62	1.1297	0.4998	1.1297	1.0629
No log	1.5238	64	0.8846	0.5699	0.8846	0.9405
No log	1.5714	66	0.8217	0.5865	0.8217	0.9065
No log	1.6190	68	0.7961	0.5412	0.7961	0.8922
No log	1.6667	70	0.8069	0.4992	0.8069	0.8983
No log	1.7143	72	0.8173	0.5306	0.8173	0.9041
No log	1.7619	74	0.8346	0.5176	0.8346	0.9136
No log	1.8095	76	0.8066	0.5148	0.8066	0.8981
No log	1.8571	78	0.8112	0.5124	0.8112	0.9007
No log	1.9048	80	0.8262	0.5353	0.8262	0.9089
No log	1.9524	82	0.9406	0.5375	0.9406	0.9698
No log	2.0	84	1.0150	0.5194	1.0150	1.0075
No log	2.0476	86	1.1340	0.5013	1.1340	1.0649
No log	2.0952	88	1.5236	0.4333	1.5236	1.2343
No log	2.1429	90	1.4901	0.4663	1.4901	1.2207
No log	2.1905	92	1.0260	0.6130	1.0260	1.0129
No log	2.2381	94	0.7283	0.6346	0.7283	0.8534
No log	2.2857	96	0.6843	0.6882	0.6843	0.8272
No log	2.3333	98	0.6784	0.6733	0.6784	0.8237
No log	2.3810	100	0.6719	0.6729	0.6719	0.8197
No log	2.4286	102	0.6728	0.6635	0.6728	0.8202
No log	2.4762	104	0.7023	0.6513	0.7023	0.8380
No log	2.5238	106	0.7799	0.6365	0.7799	0.8831
No log	2.5714	108	0.9166	0.5772	0.9166	0.9574
No log	2.6190	110	0.9610	0.5816	0.9610	0.9803
No log	2.6667	112	0.8237	0.6751	0.8237	0.9076
No log	2.7143	114	0.6557	0.7004	0.6557	0.8097
No log	2.7619	116	0.7358	0.7080	0.7358	0.8578
No log	2.8095	118	0.8297	0.6927	0.8297	0.9109
No log	2.8571	120	0.7125	0.6936	0.7125	0.8441
No log	2.9048	122	0.6546	0.6635	0.6546	0.8091
No log	2.9524	124	0.7154	0.7240	0.7154	0.8458
No log	3.0	126	0.7160	0.7261	0.7160	0.8462
No log	3.0476	128	0.6470	0.7236	0.6470	0.8044
No log	3.0952	130	0.6487	0.7033	0.6487	0.8054
No log	3.1429	132	0.6505	0.7154	0.6505	0.8065
No log	3.1905	134	0.6641	0.7223	0.6641	0.8149
No log	3.2381	136	0.6627	0.7148	0.6627	0.8141
No log	3.2857	138	0.6516	0.7112	0.6516	0.8072
No log	3.3333	140	0.6479	0.7179	0.6479	0.8049
No log	3.3810	142	0.6886	0.7449	0.6886	0.8298
No log	3.4286	144	0.7763	0.6959	0.7763	0.8811
No log	3.4762	146	0.8385	0.6942	0.8385	0.9157
No log	3.5238	148	0.8900	0.6237	0.8900	0.9434
No log	3.5714	150	0.8987	0.6437	0.8987	0.9480
No log	3.6190	152	0.9007	0.6601	0.9007	0.9490
No log	3.6667	154	0.9658	0.6065	0.9658	0.9828
No log	3.7143	156	0.9608	0.6331	0.9608	0.9802
No log	3.7619	158	0.8100	0.6678	0.8100	0.9000
No log	3.8095	160	0.6758	0.7065	0.6758	0.8221
No log	3.8571	162	0.6657	0.7332	0.6657	0.8159
No log	3.9048	164	0.6843	0.6846	0.6843	0.8272
No log	3.9524	166	0.6303	0.7281	0.6303	0.7939
No log	4.0	168	0.6492	0.7124	0.6492	0.8057
No log	4.0476	170	0.7791	0.6725	0.7791	0.8827
No log	4.0952	172	0.8075	0.6744	0.8075	0.8986
No log	4.1429	174	0.7870	0.6897	0.7870	0.8871
No log	4.1905	176	0.7435	0.7035	0.7435	0.8623
No log	4.2381	178	0.6972	0.6872	0.6972	0.8350
No log	4.2857	180	0.6920	0.7052	0.6920	0.8319
No log	4.3333	182	0.7067	0.7062	0.7067	0.8407
No log	4.3810	184	0.7440	0.7211	0.7440	0.8626
No log	4.4286	186	0.7047	0.7175	0.7047	0.8394
No log	4.4762	188	0.6971	0.7151	0.6971	0.8349
No log	4.5238	190	0.6937	0.7052	0.6937	0.8329
No log	4.5714	192	0.6783	0.7212	0.6783	0.8236
No log	4.6190	194	0.6821	0.7368	0.6821	0.8259
No log	4.6667	196	0.7148	0.6900	0.7148	0.8455
No log	4.7143	198	0.7679	0.6710	0.7679	0.8763
No log	4.7619	200	0.7922	0.6694	0.7922	0.8901
No log	4.8095	202	0.7662	0.6777	0.7662	0.8754
No log	4.8571	204	0.7436	0.6912	0.7436	0.8623
No log	4.9048	206	0.7397	0.6953	0.7397	0.8600
No log	4.9524	208	0.7530	0.6876	0.7530	0.8677
No log	5.0	210	0.7388	0.6980	0.7388	0.8595
No log	5.0476	212	0.7084	0.7217	0.7084	0.8416
No log	5.0952	214	0.7050	0.7336	0.7050	0.8397
No log	5.1429	216	0.7283	0.7015	0.7283	0.8534
No log	5.1905	218	0.7310	0.7027	0.7310	0.8550
No log	5.2381	220	0.7474	0.6928	0.7474	0.8645
No log	5.2857	222	0.7645	0.6662	0.7645	0.8744
No log	5.3333	224	0.7691	0.6662	0.7691	0.8770
No log	5.3810	226	0.8012	0.6662	0.8012	0.8951
No log	5.4286	228	0.7882	0.6979	0.7882	0.8878
No log	5.4762	230	0.7601	0.7082	0.7601	0.8718
No log	5.5238	232	0.7834	0.7055	0.7834	0.8851
No log	5.5714	234	0.8539	0.6796	0.8539	0.9240
No log	5.6190	236	0.9228	0.6394	0.9228	0.9606
No log	5.6667	238	0.9281	0.6240	0.9281	0.9634
No log	5.7143	240	0.9216	0.6245	0.9216	0.9600
No log	5.7619	242	0.8982	0.6360	0.8982	0.9477
No log	5.8095	244	0.8783	0.6464	0.8783	0.9372
No log	5.8571	246	0.8078	0.6562	0.8078	0.8988
No log	5.9048	248	0.6996	0.7360	0.6996	0.8364
No log	5.9524	250	0.6403	0.7276	0.6403	0.8002
No log	6.0	252	0.6366	0.6983	0.6366	0.7979
No log	6.0476	254	0.6558	0.7045	0.6558	0.8098
No log	6.0952	256	0.6633	0.7216	0.6633	0.8145
No log	6.1429	258	0.7156	0.7027	0.7156	0.8459
No log	6.1905	260	0.7748	0.6805	0.7748	0.8803
No log	6.2381	262	0.7944	0.6628	0.7944	0.8913
No log	6.2857	264	0.7600	0.6837	0.7600	0.8718
No log	6.3333	266	0.7470	0.6970	0.7470	0.8643
No log	6.3810	268	0.7273	0.7018	0.7273	0.8528
No log	6.4286	270	0.7315	0.7083	0.7315	0.8553
No log	6.4762	272	0.7472	0.7124	0.7472	0.8644
No log	6.5238	274	0.7797	0.6876	0.7797	0.8830
No log	6.5714	276	0.7864	0.7045	0.7864	0.8868
No log	6.6190	278	0.7934	0.6935	0.7934	0.8907
No log	6.6667	280	0.8092	0.6750	0.8092	0.8996
No log	6.7143	282	0.8517	0.6637	0.8517	0.9229
No log	6.7619	284	0.8959	0.6539	0.8959	0.9465
No log	6.8095	286	0.9247	0.6098	0.9247	0.9616
No log	6.8571	288	0.8855	0.6264	0.8855	0.9410
No log	6.9048	290	0.8489	0.6528	0.8489	0.9214
No log	6.9524	292	0.7964	0.6585	0.7964	0.8924
No log	7.0	294	0.7779	0.6797	0.7779	0.8820
No log	7.0476	296	0.7959	0.6627	0.7959	0.8921
No log	7.0952	298	0.8364	0.6570	0.8364	0.9146
No log	7.1429	300	0.8186	0.6611	0.8186	0.9048
No log	7.1905	302	0.7643	0.6892	0.7643	0.8742
No log	7.2381	304	0.7081	0.7388	0.7081	0.8415
No log	7.2857	306	0.6958	0.7395	0.6958	0.8341
No log	7.3333	308	0.6981	0.7336	0.6981	0.8355
No log	7.3810	310	0.7183	0.7482	0.7183	0.8475
No log	7.4286	312	0.7608	0.7012	0.7608	0.8722
No log	7.4762	314	0.7792	0.6780	0.7792	0.8827
No log	7.5238	316	0.7914	0.6780	0.7914	0.8896
No log	7.5714	318	0.8314	0.6846	0.8314	0.9118
No log	7.6190	320	0.8380	0.6639	0.8380	0.9154
No log	7.6667	322	0.8256	0.6680	0.8256	0.9086
No log	7.7143	324	0.8150	0.6806	0.8150	0.9028
No log	7.7619	326	0.8159	0.6806	0.8159	0.9033
No log	7.8095	328	0.8133	0.6846	0.8133	0.9018
No log	7.8571	330	0.7796	0.6957	0.7796	0.8830
No log	7.9048	332	0.7424	0.7112	0.7424	0.8616
No log	7.9524	334	0.7394	0.7112	0.7394	0.8599
No log	8.0	336	0.7323	0.7112	0.7323	0.8557
No log	8.0476	338	0.7237	0.7112	0.7237	0.8507
No log	8.0952	340	0.7218	0.7112	0.7218	0.8496
No log	8.1429	342	0.7121	0.7112	0.7121	0.8438
No log	8.1905	344	0.6919	0.7250	0.6919	0.8318
No log	8.2381	346	0.6761	0.7138	0.6761	0.8223
No log	8.2857	348	0.6636	0.7042	0.6636	0.8146
No log	8.3333	350	0.6698	0.7138	0.6698	0.8184
No log	8.3810	352	0.6929	0.7215	0.6929	0.8324
No log	8.4286	354	0.7365	0.7016	0.7365	0.8582
No log	8.4762	356	0.8045	0.6771	0.8045	0.8969
No log	8.5238	358	0.8565	0.6590	0.8565	0.9255
No log	8.5714	360	0.8738	0.6487	0.8738	0.9348
No log	8.6190	362	0.8581	0.6501	0.8581	0.9263
No log	8.6667	364	0.8300	0.6590	0.8300	0.9111
No log	8.7143	366	0.7918	0.6922	0.7918	0.8898
No log	8.7619	368	0.7551	0.7016	0.7551	0.8689
No log	8.8095	370	0.7273	0.7058	0.7273	0.8528
No log	8.8571	372	0.7236	0.7058	0.7236	0.8507
No log	8.9048	374	0.7233	0.7058	0.7233	0.8504
No log	8.9524	376	0.7302	0.7058	0.7302	0.8545
No log	9.0	378	0.7395	0.7016	0.7395	0.8599
No log	9.0476	380	0.7578	0.7016	0.7578	0.8705
No log	9.0952	382	0.7710	0.7016	0.7710	0.8781
No log	9.1429	384	0.7760	0.7016	0.7760	0.8809
No log	9.1905	386	0.7673	0.7016	0.7673	0.8760
No log	9.2381	388	0.7563	0.7016	0.7563	0.8696
No log	9.2857	390	0.7481	0.7016	0.7481	0.8649
No log	9.3333	392	0.7468	0.7058	0.7468	0.8642
No log	9.3810	394	0.7473	0.7016	0.7473	0.8645
No log	9.4286	396	0.7530	0.7016	0.7530	0.8677
No log	9.4762	398	0.7583	0.7016	0.7583	0.8708
No log	9.5238	400	0.7583	0.7016	0.7583	0.8708
No log	9.5714	402	0.7539	0.7016	0.7539	0.8682
No log	9.6190	404	0.7536	0.7016	0.7536	0.8681
No log	9.6667	406	0.7579	0.7016	0.7579	0.8706
No log	9.7143	408	0.7597	0.7016	0.7597	0.8716
No log	9.7619	410	0.7581	0.7016	0.7581	0.8707
No log	9.8095	412	0.7569	0.7016	0.7569	0.8700
No log	9.8571	414	0.7558	0.7016	0.7558	0.8694
No log	9.9048	416	0.7560	0.7016	0.7560	0.8695
No log	9.9524	418	0.7564	0.7016	0.7564	0.8697
No log	10.0	420	0.7566	0.7016	0.7566	0.8698

Framework versions

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