ArabicNewSplits5_FineTuningAraBERT_run3_AugV5_k7_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: 0.9015
• Qwk: 0.4440
• Mse: 0.9015
• Rmse: 0.9495

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	3.9079	-0.0004	3.9079	1.9768
No log	0.0870	4	1.9242	0.0594	1.9242	1.3871
No log	0.1304	6	1.2709	0.0228	1.2709	1.1273
No log	0.1739	8	1.2861	-0.0119	1.2861	1.1341
No log	0.2174	10	1.1131	0.0168	1.1131	1.0550
No log	0.2609	12	1.4534	0.0062	1.4534	1.2056
No log	0.3043	14	1.6130	0.0044	1.6130	1.2701
No log	0.3478	16	2.4023	-0.1074	2.4023	1.5499
No log	0.3913	18	1.8580	-0.0546	1.8580	1.3631
No log	0.4348	20	0.9865	0.0516	0.9865	0.9932
No log	0.4783	22	0.8442	0.1102	0.8442	0.9188
No log	0.5217	24	0.8920	0.1234	0.8920	0.9445
No log	0.5652	26	1.1489	0.0296	1.1489	1.0719
No log	0.6087	28	1.4322	0.0402	1.4322	1.1968
No log	0.6522	30	1.6283	0.0902	1.6283	1.2761
No log	0.6957	32	1.5586	0.1385	1.5586	1.2485
No log	0.7391	34	1.5629	0.1372	1.5629	1.2502
No log	0.7826	36	1.2189	0.1109	1.2189	1.1040
No log	0.8261	38	1.0270	0.1448	1.0270	1.0134
No log	0.8696	40	0.8282	0.2404	0.8282	0.9101
No log	0.9130	42	0.7782	0.2521	0.7782	0.8822
No log	0.9565	44	0.8506	0.1422	0.8506	0.9223
No log	1.0	46	0.8544	0.1353	0.8544	0.9244
No log	1.0435	48	1.0831	0.1313	1.0831	1.0407
No log	1.0870	50	1.3611	0.1630	1.3611	1.1667
No log	1.1304	52	1.2755	0.1520	1.2755	1.1294
No log	1.1739	54	1.1232	0.1418	1.1232	1.0598
No log	1.2174	56	0.8161	0.2172	0.8161	0.9034
No log	1.2609	58	0.6614	0.3878	0.6614	0.8133
No log	1.3043	60	0.6973	0.3385	0.6973	0.8350
No log	1.3478	62	0.8539	0.2356	0.8539	0.9241
No log	1.3913	64	1.3033	0.1422	1.3033	1.1416
No log	1.4348	66	1.7136	0.1300	1.7136	1.3090
No log	1.4783	68	1.8812	0.1340	1.8812	1.3716
No log	1.5217	70	1.7973	0.1527	1.7973	1.3406
No log	1.5652	72	1.6219	0.1759	1.6219	1.2735
No log	1.6087	74	1.3708	0.2307	1.3708	1.1708
No log	1.6522	76	1.1696	0.2611	1.1696	1.0815
No log	1.6957	78	1.0988	0.2190	1.0988	1.0482
No log	1.7391	80	1.0166	0.1501	1.0166	1.0083
No log	1.7826	82	0.9347	0.1740	0.9347	0.9668
No log	1.8261	84	0.8102	0.2098	0.8102	0.9001
No log	1.8696	86	0.6475	0.3649	0.6475	0.8047
No log	1.9130	88	0.6288	0.3873	0.6288	0.7930
No log	1.9565	90	0.6476	0.3816	0.6476	0.8048
No log	2.0	92	0.6383	0.3662	0.6383	0.7989
No log	2.0435	94	0.6490	0.4339	0.6490	0.8056
No log	2.0870	96	0.7540	0.3120	0.7540	0.8683
No log	2.1304	98	1.2334	0.2751	1.2334	1.1106
No log	2.1739	100	1.8931	0.1617	1.8931	1.3759
No log	2.2174	102	2.0105	0.1422	2.0105	1.4179
No log	2.2609	104	1.7890	0.1548	1.7890	1.3375
No log	2.3043	106	1.4359	0.2108	1.4359	1.1983
No log	2.3478	108	1.1186	0.2157	1.1186	1.0577
No log	2.3913	110	0.9231	0.2274	0.9231	0.9608
No log	2.4348	112	0.8098	0.2795	0.8098	0.8999
No log	2.4783	114	0.7739	0.2539	0.7739	0.8797
No log	2.5217	116	0.8155	0.2321	0.8155	0.9030
No log	2.5652	118	0.8088	0.2396	0.8088	0.8993
No log	2.6087	120	0.8334	0.2321	0.8334	0.9129
No log	2.6522	122	0.9650	0.1850	0.9650	0.9823
No log	2.6957	124	1.2025	0.1909	1.2025	1.0966
No log	2.7391	126	1.3128	0.1836	1.3128	1.1458
No log	2.7826	128	1.3669	0.2575	1.3669	1.1691
No log	2.8261	130	1.5475	0.1910	1.5475	1.2440
No log	2.8696	132	1.5569	0.2320	1.5569	1.2478
No log	2.9130	134	1.4281	0.2456	1.4281	1.1950
No log	2.9565	136	1.1143	0.3038	1.1143	1.0556
No log	3.0	138	0.9047	0.3329	0.9047	0.9512
No log	3.0435	140	0.8251	0.3174	0.8251	0.9084
No log	3.0870	142	0.8624	0.2989	0.8624	0.9287
No log	3.1304	144	0.8582	0.3105	0.8582	0.9264
No log	3.1739	146	0.7861	0.3030	0.7861	0.8866
No log	3.2174	148	0.7356	0.3519	0.7356	0.8577
No log	3.2609	150	0.7366	0.3847	0.7366	0.8583
No log	3.3043	152	0.7807	0.3400	0.7807	0.8836
No log	3.3478	154	0.9662	0.3307	0.9662	0.9829
No log	3.3913	156	1.1602	0.3030	1.1602	1.0771
No log	3.4348	158	1.3806	0.2920	1.3806	1.1750
No log	3.4783	160	1.3918	0.3078	1.3918	1.1798
No log	3.5217	162	1.0969	0.3481	1.0969	1.0473
No log	3.5652	164	0.8933	0.4544	0.8933	0.9451
No log	3.6087	166	0.7933	0.4587	0.7933	0.8907
No log	3.6522	168	0.7701	0.4633	0.7701	0.8776
No log	3.6957	170	0.8325	0.4123	0.8325	0.9124
No log	3.7391	172	0.9009	0.3546	0.9009	0.9491
No log	3.7826	174	0.8361	0.3927	0.8361	0.9144
No log	3.8261	176	0.8029	0.4041	0.8029	0.8961
No log	3.8696	178	0.8180	0.4041	0.8180	0.9044
No log	3.9130	180	0.8450	0.4084	0.8450	0.9193
No log	3.9565	182	0.8451	0.4069	0.8451	0.9193
No log	4.0	184	0.8272	0.4134	0.8272	0.9095
No log	4.0435	186	0.7723	0.3964	0.7723	0.8788
No log	4.0870	188	0.7704	0.4200	0.7704	0.8777
No log	4.1304	190	0.8785	0.4080	0.8785	0.9373
No log	4.1739	192	1.1282	0.3286	1.1282	1.0622
No log	4.2174	194	1.3329	0.3408	1.3329	1.1545
No log	4.2609	196	1.3287	0.3083	1.3287	1.1527
No log	4.3043	198	1.1370	0.3027	1.1370	1.0663
No log	4.3478	200	0.8900	0.3300	0.8900	0.9434
No log	4.3913	202	0.8178	0.4555	0.8178	0.9043
No log	4.4348	204	0.8512	0.3995	0.8512	0.9226
No log	4.4783	206	0.9745	0.3360	0.9745	0.9872
No log	4.5217	208	1.0751	0.3440	1.0751	1.0368
No log	4.5652	210	1.0831	0.3440	1.0831	1.0407
No log	4.6087	212	1.1550	0.3077	1.1550	1.0747
No log	4.6522	214	1.0530	0.3566	1.0530	1.0261
No log	4.6957	216	0.9979	0.3115	0.9979	0.9989
No log	4.7391	218	0.9393	0.3214	0.9393	0.9692
No log	4.7826	220	0.8412	0.3805	0.8412	0.9171
No log	4.8261	222	0.8005	0.4165	0.8005	0.8947
No log	4.8696	224	0.8202	0.4188	0.8202	0.9057
No log	4.9130	226	0.9162	0.4015	0.9162	0.9572
No log	4.9565	228	1.1329	0.3069	1.1329	1.0644
No log	5.0	230	1.3982	0.3229	1.3982	1.1824
No log	5.0435	232	1.4370	0.2936	1.4370	1.1987
No log	5.0870	234	1.2676	0.2968	1.2676	1.1259
No log	5.1304	236	1.0261	0.3443	1.0261	1.0130
No log	5.1739	238	0.8861	0.4211	0.8861	0.9413
No log	5.2174	240	0.8443	0.4492	0.8443	0.9189
No log	5.2609	242	0.8459	0.4342	0.8459	0.9197
No log	5.3043	244	0.8727	0.4041	0.8727	0.9342
No log	5.3478	246	0.9461	0.3840	0.9461	0.9727
No log	5.3913	248	1.0027	0.3608	1.0027	1.0013
No log	5.4348	250	1.0883	0.3214	1.0883	1.0432
No log	5.4783	252	1.2796	0.3058	1.2796	1.1312
No log	5.5217	254	1.4938	0.2626	1.4938	1.2222
No log	5.5652	256	1.5797	0.2214	1.5797	1.2568
No log	5.6087	258	1.4562	0.2787	1.4562	1.2067
No log	5.6522	260	1.2561	0.3471	1.2561	1.1208
No log	5.6957	262	1.0600	0.3760	1.0600	1.0295
No log	5.7391	264	0.9788	0.4079	0.9788	0.9893
No log	5.7826	266	0.9923	0.4067	0.9923	0.9961
No log	5.8261	268	1.1057	0.3608	1.1057	1.0515
No log	5.8696	270	1.2273	0.3260	1.2273	1.1078
No log	5.9130	272	1.3049	0.2777	1.3049	1.1423
No log	5.9565	274	1.3867	0.2873	1.3867	1.1776
No log	6.0	276	1.3442	0.2924	1.3442	1.1594
No log	6.0435	278	1.2146	0.2789	1.2146	1.1021
No log	6.0870	280	1.0662	0.3334	1.0662	1.0326
No log	6.1304	282	0.9451	0.3890	0.9451	0.9722
No log	6.1739	284	0.9122	0.4056	0.9122	0.9551
No log	6.2174	286	0.9107	0.4521	0.9107	0.9543
No log	6.2609	288	0.9535	0.4253	0.9535	0.9765
No log	6.3043	290	0.9766	0.3878	0.9766	0.9882
No log	6.3478	292	0.9728	0.3560	0.9728	0.9863
No log	6.3913	294	0.9613	0.3789	0.9613	0.9804
No log	6.4348	296	0.9771	0.3813	0.9771	0.9885
No log	6.4783	298	1.0311	0.3654	1.0311	1.0154
No log	6.5217	300	1.1202	0.3363	1.1202	1.0584
No log	6.5652	302	1.1413	0.3297	1.1413	1.0683
No log	6.6087	304	1.0651	0.3614	1.0651	1.0320
No log	6.6522	306	0.9685	0.3578	0.9685	0.9841
No log	6.6957	308	0.8825	0.4014	0.8825	0.9394
No log	6.7391	310	0.8353	0.4150	0.8353	0.9139
No log	6.7826	312	0.8355	0.4015	0.8355	0.9141
No log	6.8261	314	0.8821	0.4075	0.8821	0.9392
No log	6.8696	316	0.9648	0.4136	0.9648	0.9823
No log	6.9130	318	0.9987	0.3935	0.9987	0.9994
No log	6.9565	320	0.9772	0.3923	0.9772	0.9885
No log	7.0	322	0.9183	0.4220	0.9183	0.9583
No log	7.0435	324	0.8857	0.3954	0.8857	0.9411
No log	7.0870	326	0.8892	0.4024	0.8892	0.9430
No log	7.1304	328	0.8999	0.4113	0.8999	0.9486
No log	7.1739	330	0.9097	0.4011	0.9097	0.9538
No log	7.2174	332	0.9271	0.4030	0.9271	0.9628
No log	7.2609	334	0.9096	0.4011	0.9096	0.9537
No log	7.3043	336	0.9123	0.4030	0.9123	0.9551
No log	7.3478	338	0.9069	0.4030	0.9069	0.9523
No log	7.3913	340	0.9118	0.4149	0.9118	0.9549
No log	7.4348	342	0.9298	0.4044	0.9298	0.9643
No log	7.4783	344	0.9338	0.4080	0.9338	0.9663
No log	7.5217	346	0.9185	0.3984	0.9185	0.9584
No log	7.5652	348	0.8922	0.4219	0.8922	0.9446
No log	7.6087	350	0.8576	0.3964	0.8576	0.9261
No log	7.6522	352	0.8287	0.4081	0.8287	0.9103
No log	7.6957	354	0.8229	0.4725	0.8229	0.9071
No log	7.7391	356	0.8386	0.4461	0.8386	0.9157
No log	7.7826	358	0.8603	0.4626	0.8603	0.9275
No log	7.8261	360	0.8958	0.4410	0.8958	0.9465
No log	7.8696	362	0.9198	0.4072	0.9198	0.9590
No log	7.9130	364	0.9414	0.3970	0.9414	0.9703
No log	7.9565	366	0.9401	0.3970	0.9401	0.9696
No log	8.0	368	0.9244	0.4072	0.9244	0.9615
No log	8.0435	370	0.9142	0.4072	0.9142	0.9562
No log	8.0870	372	0.9225	0.4072	0.9225	0.9605
No log	8.1304	374	0.9168	0.4198	0.9168	0.9575
No log	8.1739	376	0.9056	0.4198	0.9056	0.9516
No log	8.2174	378	0.9142	0.4198	0.9142	0.9561
No log	8.2609	380	0.9378	0.3970	0.9378	0.9684
No log	8.3043	382	0.9694	0.4009	0.9694	0.9846
No log	8.3478	384	0.9663	0.4009	0.9663	0.9830
No log	8.3913	386	0.9672	0.4009	0.9672	0.9835
No log	8.4348	388	0.9523	0.3989	0.9523	0.9758
No log	8.4783	390	0.9440	0.4072	0.9440	0.9716
No log	8.5217	392	0.9413	0.4198	0.9413	0.9702
No log	8.5652	394	0.9280	0.4198	0.9280	0.9633
No log	8.6087	396	0.9297	0.4198	0.9297	0.9642
No log	8.6522	398	0.9262	0.4372	0.9262	0.9624
No log	8.6957	400	0.9144	0.4425	0.9144	0.9562
No log	8.7391	402	0.9073	0.4425	0.9073	0.9525
No log	8.7826	404	0.9034	0.4372	0.9034	0.9505
No log	8.8261	406	0.8992	0.4372	0.8992	0.9483
No log	8.8696	408	0.8958	0.4074	0.8958	0.9465
No log	8.9130	410	0.8941	0.3838	0.8941	0.9456
No log	8.9565	412	0.9013	0.3806	0.9013	0.9494
No log	9.0	414	0.9200	0.3902	0.9200	0.9592
No log	9.0435	416	0.9460	0.3870	0.9460	0.9726
No log	9.0870	418	0.9713	0.4170	0.9713	0.9856
No log	9.1304	420	0.9763	0.4170	0.9763	0.9881
No log	9.1739	422	0.9680	0.4204	0.9680	0.9839
No log	9.2174	424	0.9523	0.4187	0.9523	0.9758
No log	9.2609	426	0.9340	0.3976	0.9340	0.9664
No log	9.3043	428	0.9145	0.3795	0.9145	0.9563
No log	9.3478	430	0.8998	0.4179	0.8998	0.9486
No log	9.3913	432	0.8911	0.4462	0.8911	0.9440
No log	9.4348	434	0.8857	0.4319	0.8857	0.9411
No log	9.4783	436	0.8833	0.4247	0.8833	0.9398
No log	9.5217	438	0.8827	0.4175	0.8827	0.9395
No log	9.5652	440	0.8854	0.4175	0.8854	0.9409
No log	9.6087	442	0.8877	0.4175	0.8877	0.9422
No log	9.6522	444	0.8885	0.4175	0.8885	0.9426
No log	9.6957	446	0.8898	0.4247	0.8898	0.9433
No log	9.7391	448	0.8908	0.4319	0.8908	0.9438
No log	9.7826	450	0.8931	0.4319	0.8931	0.9451
No log	9.8261	452	0.8961	0.4336	0.8961	0.9466
No log	9.8696	454	0.8977	0.4336	0.8977	0.9475
No log	9.9130	456	0.8997	0.4353	0.8997	0.9485
No log	9.9565	458	0.9010	0.4440	0.9010	0.9492
No log	10.0	460	0.9015	0.4440	0.9015	0.9495

Framework versions

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