ArabicNewSplits5_FineTuningAraBERT_run1_AugV5_k5_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: 0.9387
• Qwk: 0.4346
• Mse: 0.9387
• Rmse: 0.9689

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	0.0588	2	4.0665	-0.0151	4.0665	2.0166
No log	0.1176	4	2.0305	0.0284	2.0305	1.4250
No log	0.1765	6	1.1765	0.0592	1.1765	1.0846
No log	0.2353	8	0.8194	0.0770	0.8194	0.9052
No log	0.2941	10	0.9559	0.1514	0.9559	0.9777
No log	0.3529	12	1.1527	0.1040	1.1527	1.0736
No log	0.4118	14	0.8714	0.1748	0.8714	0.9335
No log	0.4706	16	0.6749	0.2880	0.6749	0.8215
No log	0.5294	18	0.6440	0.3611	0.6440	0.8025
No log	0.5882	20	0.8069	0.1337	0.8069	0.8983
No log	0.6471	22	0.9382	0.1106	0.9382	0.9686
No log	0.7059	24	0.9534	0.1590	0.9534	0.9764
No log	0.7647	26	1.1871	0.1583	1.1871	1.0895
No log	0.8235	28	1.5034	0.1392	1.5034	1.2261
No log	0.8824	30	1.8216	0.1717	1.8216	1.3497
No log	0.9412	32	1.7859	0.1794	1.7859	1.3364
No log	1.0	34	1.4960	0.1639	1.4960	1.2231
No log	1.0588	36	1.7451	0.1670	1.7451	1.3210
No log	1.1176	38	1.6910	0.1884	1.6910	1.3004
No log	1.1765	40	1.3136	0.1579	1.3136	1.1461
No log	1.2353	42	1.0181	0.1786	1.0181	1.0090
No log	1.2941	44	0.9802	0.2295	0.9802	0.9900
No log	1.3529	46	0.9418	0.2887	0.9418	0.9704
No log	1.4118	48	0.8933	0.2487	0.8933	0.9451
No log	1.4706	50	0.8008	0.2508	0.8008	0.8949
No log	1.5294	52	0.7552	0.3298	0.7552	0.8690
No log	1.5882	54	0.9062	0.2864	0.9062	0.9520
No log	1.6471	56	1.0425	0.1967	1.0425	1.0210
No log	1.7059	58	1.0477	0.2196	1.0477	1.0236
No log	1.7647	60	0.9542	0.2626	0.9542	0.9769
No log	1.8235	62	0.8922	0.2739	0.8922	0.9446
No log	1.8824	64	0.8045	0.3342	0.8045	0.8969
No log	1.9412	66	0.7611	0.3828	0.7611	0.8724
No log	2.0	68	0.7806	0.3835	0.7806	0.8835
No log	2.0588	70	0.8746	0.3877	0.8746	0.9352
No log	2.1176	72	1.0062	0.3381	1.0062	1.0031
No log	2.1765	74	1.2002	0.3087	1.2002	1.0955
No log	2.2353	76	1.1859	0.3109	1.1859	1.0890
No log	2.2941	78	0.8804	0.4553	0.8804	0.9383
No log	2.3529	80	0.7851	0.4756	0.7851	0.8860
No log	2.4118	82	0.7514	0.4407	0.7514	0.8668
No log	2.4706	84	0.7220	0.4470	0.7220	0.8497
No log	2.5294	86	0.6965	0.4655	0.6965	0.8346
No log	2.5882	88	0.6990	0.4789	0.6990	0.8360
No log	2.6471	90	0.8786	0.4517	0.8786	0.9373
No log	2.7059	92	1.2701	0.2916	1.2701	1.1270
No log	2.7647	94	1.4689	0.2385	1.4689	1.2120
No log	2.8235	96	1.3729	0.2553	1.3729	1.1717
No log	2.8824	98	1.0169	0.3935	1.0169	1.0084
No log	2.9412	100	0.6982	0.5465	0.6982	0.8356
No log	3.0	102	0.7005	0.5664	0.7005	0.8369
No log	3.0588	104	0.7189	0.5061	0.7189	0.8479
No log	3.1176	106	0.7028	0.5024	0.7028	0.8383
No log	3.1765	108	0.6616	0.5748	0.6616	0.8134
No log	3.2353	110	0.6902	0.5839	0.6902	0.8308
No log	3.2941	112	0.7648	0.5466	0.7648	0.8745
No log	3.3529	114	0.7680	0.5368	0.7680	0.8764
No log	3.4118	116	0.7914	0.5440	0.7914	0.8896
No log	3.4706	118	0.8295	0.5099	0.8295	0.9107
No log	3.5294	120	0.8752	0.5291	0.8752	0.9355
No log	3.5882	122	0.9250	0.5036	0.9250	0.9617
No log	3.6471	124	0.9585	0.4668	0.9585	0.9790
No log	3.7059	126	1.0455	0.4595	1.0455	1.0225
No log	3.7647	128	1.0704	0.4356	1.0704	1.0346
No log	3.8235	130	1.0678	0.4522	1.0678	1.0333
No log	3.8824	132	1.0560	0.4662	1.0560	1.0276
No log	3.9412	134	1.0661	0.4728	1.0661	1.0325
No log	4.0	136	1.1035	0.4522	1.1035	1.0505
No log	4.0588	138	1.1184	0.4426	1.1184	1.0576
No log	4.1176	140	1.1446	0.4759	1.1446	1.0699
No log	4.1765	142	1.1757	0.4452	1.1757	1.0843
No log	4.2353	144	1.1946	0.4615	1.1946	1.0930
No log	4.2941	146	1.1838	0.4350	1.1838	1.0880
No log	4.3529	148	1.2254	0.4234	1.2254	1.1070
No log	4.4118	150	1.2148	0.3912	1.2148	1.1022
No log	4.4706	152	1.1693	0.3925	1.1693	1.0813
No log	4.5294	154	1.1186	0.4257	1.1186	1.0577
No log	4.5882	156	1.0553	0.4358	1.0553	1.0273
No log	4.6471	158	1.0427	0.4691	1.0427	1.0211
No log	4.7059	160	1.0303	0.4311	1.0303	1.0150
No log	4.7647	162	0.9643	0.4310	0.9643	0.9820
No log	4.8235	164	0.9096	0.5018	0.9096	0.9537
No log	4.8824	166	0.8893	0.4318	0.8893	0.9430
No log	4.9412	168	0.9167	0.3801	0.9167	0.9574
No log	5.0	170	0.9512	0.4179	0.9512	0.9753
No log	5.0588	172	0.9828	0.4340	0.9828	0.9914
No log	5.1176	174	1.0007	0.5042	1.0007	1.0003
No log	5.1765	176	1.0242	0.4682	1.0242	1.0120
No log	5.2353	178	1.0493	0.4440	1.0493	1.0244
No log	5.2941	180	1.0712	0.4496	1.0712	1.0350
No log	5.3529	182	1.0768	0.4695	1.0768	1.0377
No log	5.4118	184	1.1345	0.4464	1.1345	1.0651
No log	5.4706	186	1.2182	0.4129	1.2182	1.1037
No log	5.5294	188	1.2162	0.4129	1.2162	1.1028
No log	5.5882	190	1.1601	0.4531	1.1601	1.0771
No log	5.6471	192	1.0941	0.4381	1.0941	1.0460
No log	5.7059	194	1.0678	0.4671	1.0678	1.0334
No log	5.7647	196	1.0822	0.4452	1.0822	1.0403
No log	5.8235	198	1.1089	0.4654	1.1089	1.0530
No log	5.8824	200	1.1277	0.4701	1.1277	1.0619
No log	5.9412	202	1.1231	0.3850	1.1231	1.0598
No log	6.0	204	1.1071	0.3996	1.1071	1.0522
No log	6.0588	206	1.0830	0.4187	1.0830	1.0407
No log	6.1176	208	1.0420	0.4279	1.0420	1.0208
No log	6.1765	210	1.0035	0.4641	1.0035	1.0017
No log	6.2353	212	0.9808	0.4752	0.9808	0.9903
No log	6.2941	214	0.9835	0.4471	0.9835	0.9917
No log	6.3529	216	0.9981	0.4305	0.9981	0.9991
No log	6.4118	218	0.9881	0.4448	0.9881	0.9940
No log	6.4706	220	0.9810	0.4476	0.9810	0.9905
No log	6.5294	222	0.9927	0.4613	0.9927	0.9964
No log	6.5882	224	1.0113	0.4613	1.0113	1.0056
No log	6.6471	226	1.0283	0.4534	1.0283	1.0141
No log	6.7059	228	1.0610	0.4410	1.0610	1.0301
No log	6.7647	230	1.0927	0.4420	1.0927	1.0453
No log	6.8235	232	1.1058	0.4420	1.1058	1.0516
No log	6.8824	234	1.0999	0.4582	1.0999	1.0488
No log	6.9412	236	1.0817	0.4517	1.0817	1.0400
No log	7.0	238	1.0623	0.4353	1.0623	1.0307
No log	7.0588	240	1.0303	0.4384	1.0303	1.0150
No log	7.1176	242	1.0032	0.4506	1.0032	1.0016
No log	7.1765	244	0.9903	0.4777	0.9903	0.9952
No log	7.2353	246	0.9897	0.4814	0.9897	0.9948
No log	7.2941	248	0.9998	0.4681	0.9998	0.9999
No log	7.3529	250	1.0065	0.4719	1.0065	1.0032
No log	7.4118	252	1.0130	0.4759	1.0130	1.0065
No log	7.4706	254	1.0126	0.4692	1.0126	1.0063
No log	7.5294	256	1.0047	0.4784	1.0047	1.0023
No log	7.5882	258	0.9931	0.4863	0.9931	0.9965
No log	7.6471	260	0.9850	0.4880	0.9850	0.9925
No log	7.7059	262	0.9809	0.4973	0.9809	0.9904
No log	7.7647	264	0.9903	0.4628	0.9903	0.9952
No log	7.8235	266	1.0041	0.4702	1.0041	1.0020
No log	7.8824	268	1.0068	0.4642	1.0068	1.0034
No log	7.9412	270	1.0026	0.4718	1.0026	1.0013
No log	8.0	272	0.9946	0.4987	0.9946	0.9973
No log	8.0588	274	0.9798	0.4897	0.9798	0.9898
No log	8.1176	276	0.9671	0.4889	0.9671	0.9834
No log	8.1765	278	0.9706	0.4912	0.9706	0.9852
No log	8.2353	280	0.9742	0.4941	0.9742	0.9870
No log	8.2941	282	0.9839	0.4859	0.9839	0.9919
No log	8.3529	284	0.9976	0.4685	0.9976	0.9988
No log	8.4118	286	1.0005	0.4685	1.0005	1.0003
No log	8.4706	288	0.9985	0.4625	0.9985	0.9992
No log	8.5294	290	0.9951	0.4625	0.9951	0.9975
No log	8.5882	292	0.9873	0.4625	0.9873	0.9936
No log	8.6471	294	0.9776	0.4625	0.9776	0.9887
No log	8.7059	296	0.9681	0.4718	0.9681	0.9839
No log	8.7647	298	0.9612	0.4575	0.9612	0.9804
No log	8.8235	300	0.9530	0.4471	0.9530	0.9762
No log	8.8824	302	0.9526	0.4469	0.9526	0.9760
No log	8.9412	304	0.9533	0.4469	0.9533	0.9764
No log	9.0	306	0.9515	0.4471	0.9515	0.9755
No log	9.0588	308	0.9477	0.4649	0.9477	0.9735
No log	9.1176	310	0.9411	0.4649	0.9411	0.9701
No log	9.1765	312	0.9368	0.4585	0.9368	0.9679
No log	9.2353	314	0.9372	0.4585	0.9372	0.9681
No log	9.2941	316	0.9377	0.4475	0.9377	0.9684
No log	9.3529	318	0.9402	0.4572	0.9402	0.9696
No log	9.4118	320	0.9394	0.4457	0.9394	0.9692
No log	9.4706	322	0.9368	0.4457	0.9368	0.9679
No log	9.5294	324	0.9354	0.4329	0.9354	0.9672
No log	9.5882	326	0.9356	0.4329	0.9356	0.9672
No log	9.6471	328	0.9374	0.4329	0.9374	0.9682
No log	9.7059	330	0.9376	0.4329	0.9376	0.9683
No log	9.7647	332	0.9379	0.4457	0.9379	0.9684
No log	9.8235	334	0.9381	0.4457	0.9381	0.9686
No log	9.8824	336	0.9384	0.4346	0.9384	0.9687
No log	9.9412	338	0.9386	0.4346	0.9386	0.9688
No log	10.0	340	0.9387	0.4346	0.9387	0.9689

Framework versions

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