ArabicNewSplits6_FineTuningAraBERT_run2_AugV5_k9_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: 0.8770
• Qwk: 0.6081
• Mse: 0.8770
• Rmse: 0.9365

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	5.2333	-0.0180	5.2333	2.2876
No log	0.0870	4	3.1825	0.0391	3.1825	1.7840
No log	0.1304	6	2.8787	-0.1357	2.8787	1.6967
No log	0.1739	8	2.3677	-0.1851	2.3677	1.5387
No log	0.2174	10	2.3110	-0.1646	2.3110	1.5202
No log	0.2609	12	1.7196	-0.0695	1.7196	1.3114
No log	0.3043	14	1.3956	0.1178	1.3956	1.1814
No log	0.3478	16	1.4013	0.1003	1.4013	1.1838
No log	0.3913	18	1.5000	0.0900	1.5000	1.2248
No log	0.4348	20	1.6931	0.0830	1.6931	1.3012
No log	0.4783	22	1.5834	0.1197	1.5834	1.2583
No log	0.5217	24	1.1531	0.3660	1.1531	1.0738
No log	0.5652	26	1.0708	0.3897	1.0708	1.0348
No log	0.6087	28	1.0808	0.4112	1.0808	1.0396
No log	0.6522	30	1.0878	0.4081	1.0878	1.0430
No log	0.6957	32	1.0596	0.4304	1.0596	1.0294
No log	0.7391	34	1.0644	0.3929	1.0644	1.0317
No log	0.7826	36	1.1339	0.3232	1.1339	1.0649
No log	0.8261	38	1.1431	0.3291	1.1431	1.0692
No log	0.8696	40	1.0407	0.4047	1.0407	1.0201
No log	0.9130	42	0.9278	0.4373	0.9278	0.9632
No log	0.9565	44	0.9187	0.4373	0.9187	0.9585
No log	1.0	46	0.9713	0.4378	0.9713	0.9855
No log	1.0435	48	1.0131	0.4378	1.0131	1.0065
No log	1.0870	50	1.1490	0.4728	1.1490	1.0719
No log	1.1304	52	1.0564	0.4313	1.0564	1.0278
No log	1.1739	54	1.0194	0.4622	1.0194	1.0097
No log	1.2174	56	0.9321	0.4634	0.9321	0.9654
No log	1.2609	58	0.8723	0.4615	0.8723	0.9340
No log	1.3043	60	0.8640	0.5136	0.8640	0.9295
No log	1.3478	62	0.8481	0.5246	0.8481	0.9209
No log	1.3913	64	0.8386	0.5251	0.8386	0.9157
No log	1.4348	66	0.8320	0.5278	0.8320	0.9121
No log	1.4783	68	0.8307	0.5332	0.8307	0.9114
No log	1.5217	70	0.8446	0.5063	0.8446	0.9190
No log	1.5652	72	0.8320	0.5388	0.8320	0.9122
No log	1.6087	74	0.9073	0.5226	0.9073	0.9525
No log	1.6522	76	1.0215	0.4392	1.0215	1.0107
No log	1.6957	78	0.9834	0.4286	0.9834	0.9916
No log	1.7391	80	0.8480	0.5466	0.8480	0.9209
No log	1.7826	82	0.8802	0.5263	0.8802	0.9382
No log	1.8261	84	1.0555	0.4657	1.0555	1.0274
No log	1.8696	86	1.0382	0.4643	1.0382	1.0189
No log	1.9130	88	0.8332	0.5206	0.8332	0.9128
No log	1.9565	90	0.8223	0.5263	0.8223	0.9068
No log	2.0	92	1.0193	0.4471	1.0193	1.0096
No log	2.0435	94	1.1462	0.3810	1.1462	1.0706
No log	2.0870	96	1.0897	0.4771	1.0897	1.0439
No log	2.1304	98	0.9055	0.5523	0.9055	0.9516
No log	2.1739	100	0.7904	0.5921	0.7904	0.8891
No log	2.2174	102	0.8229	0.5511	0.8229	0.9071
No log	2.2609	104	0.8503	0.5445	0.8503	0.9221
No log	2.3043	106	0.8132	0.5476	0.8132	0.9018
No log	2.3478	108	0.8318	0.5637	0.8318	0.9120
No log	2.3913	110	0.8414	0.5355	0.8414	0.9173
No log	2.4348	112	0.8375	0.5611	0.8375	0.9151
No log	2.4783	114	0.8419	0.5977	0.8419	0.9176
No log	2.5217	116	0.8444	0.6352	0.8444	0.9189
No log	2.5652	118	0.8739	0.6194	0.8739	0.9348
No log	2.6087	120	0.8316	0.6456	0.8316	0.9119
No log	2.6522	122	0.7927	0.6388	0.7927	0.8903
No log	2.6957	124	0.7962	0.6499	0.7962	0.8923
No log	2.7391	126	0.8454	0.6326	0.8454	0.9194
No log	2.7826	128	1.0188	0.5300	1.0188	1.0093
No log	2.8261	130	1.1751	0.4548	1.1751	1.0840
No log	2.8696	132	1.0966	0.4684	1.0966	1.0472
No log	2.9130	134	0.8517	0.6116	0.8517	0.9229
No log	2.9565	136	0.7312	0.6230	0.7312	0.8551
No log	3.0	138	0.7924	0.5916	0.7924	0.8902
No log	3.0435	140	0.7557	0.6009	0.7557	0.8693
No log	3.0870	142	0.6908	0.6401	0.6908	0.8311
No log	3.1304	144	0.9046	0.5923	0.9046	0.9511
No log	3.1739	146	1.1016	0.4581	1.1016	1.0496
No log	3.2174	148	1.1128	0.4507	1.1128	1.0549
No log	3.2609	150	0.9066	0.5718	0.9066	0.9521
No log	3.3043	152	0.7434	0.6310	0.7434	0.8622
No log	3.3478	154	0.8946	0.5739	0.8946	0.9458
No log	3.3913	156	0.9479	0.5515	0.9479	0.9736
No log	3.4348	158	0.8049	0.6522	0.8049	0.8972
No log	3.4783	160	0.8430	0.6313	0.8430	0.9182
No log	3.5217	162	0.9510	0.5780	0.9510	0.9752
No log	3.5652	164	1.0142	0.5286	1.0142	1.0071
No log	3.6087	166	1.0605	0.5246	1.0605	1.0298
No log	3.6522	168	1.0492	0.5146	1.0492	1.0243
No log	3.6957	170	0.9977	0.5638	0.9977	0.9989
No log	3.7391	172	0.9251	0.5867	0.9251	0.9618
No log	3.7826	174	0.9351	0.5653	0.9351	0.9670
No log	3.8261	176	0.9207	0.5880	0.9207	0.9595
No log	3.8696	178	0.9075	0.5925	0.9075	0.9526
No log	3.9130	180	0.9218	0.5743	0.9218	0.9601
No log	3.9565	182	0.9257	0.5822	0.9257	0.9622
No log	4.0	184	0.9061	0.5773	0.9061	0.9519
No log	4.0435	186	0.8825	0.6027	0.8825	0.9394
No log	4.0870	188	0.8657	0.6495	0.8657	0.9304
No log	4.1304	190	0.8930	0.6036	0.8930	0.9450
No log	4.1739	192	0.9836	0.5714	0.9836	0.9918
No log	4.2174	194	1.1092	0.5084	1.1092	1.0532
No log	4.2609	196	1.1485	0.5112	1.1485	1.0717
No log	4.3043	198	1.1194	0.5120	1.1194	1.0580
No log	4.3478	200	1.0303	0.5582	1.0303	1.0150
No log	4.3913	202	0.9861	0.5724	0.9861	0.9930
No log	4.4348	204	0.9832	0.5656	0.9832	0.9916
No log	4.4783	206	1.0437	0.5246	1.0437	1.0216
No log	4.5217	208	1.0425	0.5404	1.0425	1.0210
No log	4.5652	210	1.0174	0.5520	1.0174	1.0087
No log	4.6087	212	0.8864	0.6276	0.8864	0.9415
No log	4.6522	214	0.7719	0.6539	0.7719	0.8786
No log	4.6957	216	0.7081	0.6775	0.7081	0.8415
No log	4.7391	218	0.7005	0.6763	0.7005	0.8369
No log	4.7826	220	0.7770	0.6656	0.7770	0.8815
No log	4.8261	222	0.8548	0.6643	0.8548	0.9245
No log	4.8696	224	0.8844	0.6506	0.8844	0.9404
No log	4.9130	226	0.8299	0.6597	0.8299	0.9110
No log	4.9565	228	0.7721	0.6728	0.7721	0.8787
No log	5.0	230	0.7664	0.6804	0.7664	0.8754
No log	5.0435	232	0.7957	0.6801	0.7957	0.8920
No log	5.0870	234	0.8496	0.6766	0.8496	0.9218
No log	5.1304	236	0.9393	0.6049	0.9393	0.9692
No log	5.1739	238	0.9328	0.6049	0.9328	0.9658
No log	5.2174	240	0.8494	0.6826	0.8494	0.9216
No log	5.2609	242	0.7662	0.7012	0.7662	0.8753
No log	5.3043	244	0.7563	0.6927	0.7563	0.8697
No log	5.3478	246	0.7883	0.6958	0.7883	0.8879
No log	5.3913	248	0.8490	0.6949	0.8490	0.9214
No log	5.4348	250	0.8925	0.6581	0.8925	0.9447
No log	5.4783	252	0.8793	0.6742	0.8793	0.9377
No log	5.5217	254	0.8690	0.6811	0.8690	0.9322
No log	5.5652	256	0.8483	0.6866	0.8483	0.9210
No log	5.6087	258	0.7868	0.7224	0.7868	0.8870
No log	5.6522	260	0.7384	0.6914	0.7384	0.8593
No log	5.6957	262	0.7469	0.6914	0.7469	0.8642
No log	5.7391	264	0.8237	0.7239	0.8237	0.9076
No log	5.7826	266	0.8747	0.6409	0.8747	0.9352
No log	5.8261	268	0.9176	0.6376	0.9176	0.9579
No log	5.8696	270	0.9775	0.5852	0.9775	0.9887
No log	5.9130	272	1.0477	0.5581	1.0477	1.0236
No log	5.9565	274	1.0379	0.5581	1.0379	1.0188
No log	6.0	276	0.9193	0.6041	0.9193	0.9588
No log	6.0435	278	0.7924	0.7104	0.7924	0.8902
No log	6.0870	280	0.7572	0.7092	0.7572	0.8702
No log	6.1304	282	0.7691	0.7060	0.7691	0.8770
No log	6.1739	284	0.7509	0.7060	0.7509	0.8665
No log	6.2174	286	0.7628	0.6910	0.7628	0.8734
No log	6.2609	288	0.8130	0.6495	0.8130	0.9016
No log	6.3043	290	0.7977	0.6605	0.7977	0.8931
No log	6.3478	292	0.7958	0.6605	0.7958	0.8921
No log	6.3913	294	0.8123	0.6495	0.8123	0.9013
No log	6.4348	296	0.8100	0.6495	0.8100	0.9000
No log	6.4783	298	0.8029	0.6729	0.8029	0.8960
No log	6.5217	300	0.8062	0.6658	0.8062	0.8979
No log	6.5652	302	0.8068	0.6658	0.8068	0.8982
No log	6.6087	304	0.7995	0.6696	0.7995	0.8942
No log	6.6522	306	0.8325	0.6183	0.8325	0.9124
No log	6.6957	308	0.9174	0.6224	0.9174	0.9578
No log	6.7391	310	1.0119	0.5727	1.0119	1.0059
No log	6.7826	312	1.1511	0.5185	1.1511	1.0729
No log	6.8261	314	1.1674	0.5097	1.1674	1.0804
No log	6.8696	316	1.0694	0.5440	1.0694	1.0341
No log	6.9130	318	0.9430	0.5889	0.9430	0.9711
No log	6.9565	320	0.8380	0.6377	0.8380	0.9154
No log	7.0	322	0.7801	0.6748	0.7801	0.8832
No log	7.0435	324	0.7970	0.6898	0.7970	0.8928
No log	7.0870	326	0.8031	0.6852	0.8031	0.8962
No log	7.1304	328	0.8540	0.6513	0.8540	0.9241
No log	7.1739	330	0.9553	0.5935	0.9553	0.9774
No log	7.2174	332	1.0662	0.5269	1.0662	1.0326
No log	7.2609	334	1.0953	0.5269	1.0953	1.0466
No log	7.3043	336	1.0405	0.5484	1.0405	1.0200
No log	7.3478	338	0.9830	0.5784	0.9830	0.9915
No log	7.3913	340	0.9079	0.6160	0.9079	0.9528
No log	7.4348	342	0.8294	0.6732	0.8294	0.9107
No log	7.4783	344	0.7875	0.6951	0.7875	0.8874
No log	7.5217	346	0.7940	0.6951	0.7940	0.8911
No log	7.5652	348	0.8347	0.6903	0.8347	0.9136
No log	7.6087	350	0.9251	0.6081	0.9251	0.9618
No log	7.6522	352	0.9799	0.5610	0.9799	0.9899
No log	7.6957	354	0.9778	0.5640	0.9778	0.9888
No log	7.7391	356	0.9211	0.6029	0.9211	0.9597
No log	7.7826	358	0.8505	0.6530	0.8505	0.9222
No log	7.8261	360	0.7944	0.7019	0.7944	0.8913
No log	7.8696	362	0.7754	0.7074	0.7754	0.8806
No log	7.9130	364	0.7659	0.7074	0.7659	0.8752
No log	7.9565	366	0.7732	0.7027	0.7732	0.8793
No log	8.0	368	0.7986	0.7075	0.7986	0.8936
No log	8.0435	370	0.8446	0.6771	0.8446	0.9190
No log	8.0870	372	0.8731	0.6339	0.8731	0.9344
No log	8.1304	374	0.8776	0.6339	0.8776	0.9368
No log	8.1739	376	0.8533	0.6735	0.8533	0.9238
No log	8.2174	378	0.8114	0.7027	0.8114	0.9008
No log	8.2609	380	0.7873	0.6869	0.7873	0.8873
No log	8.3043	382	0.7903	0.6869	0.7903	0.8890
No log	8.3478	384	0.7877	0.6869	0.7877	0.8875
No log	8.3913	386	0.7947	0.6869	0.7947	0.8915
No log	8.4348	388	0.8034	0.6869	0.8034	0.8963
No log	8.4783	390	0.8264	0.6771	0.8264	0.9090
No log	8.5217	392	0.8423	0.6648	0.8423	0.9178
No log	8.5652	394	0.8504	0.6648	0.8504	0.9222
No log	8.6087	396	0.8431	0.6648	0.8431	0.9182
No log	8.6522	398	0.8517	0.6260	0.8517	0.9229
No log	8.6957	400	0.8705	0.6071	0.8705	0.9330
No log	8.7391	402	0.8642	0.6369	0.8642	0.9296
No log	8.7826	404	0.8607	0.6369	0.8607	0.9277
No log	8.8261	406	0.8532	0.6369	0.8532	0.9237
No log	8.8696	408	0.8663	0.6247	0.8663	0.9308
No log	8.9130	410	0.8824	0.6155	0.8824	0.9394
No log	8.9565	412	0.9210	0.6082	0.9210	0.9597
No log	9.0	414	0.9472	0.5887	0.9472	0.9733
No log	9.0435	416	0.9527	0.5875	0.9527	0.9761
No log	9.0870	418	0.9538	0.5911	0.9538	0.9767
No log	9.1304	420	0.9403	0.5875	0.9403	0.9697
No log	9.1739	422	0.9280	0.5978	0.9280	0.9633
No log	9.2174	424	0.9174	0.6056	0.9174	0.9578
No log	9.2609	426	0.9037	0.6058	0.9037	0.9506
No log	9.3043	428	0.8978	0.6058	0.8978	0.9475
No log	9.3478	430	0.8997	0.5920	0.8997	0.9485
No log	9.3913	432	0.9035	0.5920	0.9035	0.9505
No log	9.4348	434	0.9071	0.5923	0.9071	0.9524
No log	9.4783	436	0.9105	0.5960	0.9105	0.9542
No log	9.5217	438	0.9148	0.5960	0.9148	0.9565
No log	9.5652	440	0.9123	0.5960	0.9123	0.9551
No log	9.6087	442	0.9054	0.6058	0.9054	0.9515
No log	9.6522	444	0.8966	0.6020	0.8966	0.9469
No log	9.6957	446	0.8908	0.6081	0.8908	0.9438
No log	9.7391	448	0.8845	0.6081	0.8845	0.9405
No log	9.7826	450	0.8785	0.6081	0.8785	0.9373
No log	9.8261	452	0.8762	0.6081	0.8762	0.9360
No log	9.8696	454	0.8749	0.6081	0.8749	0.9354
No log	9.9130	456	0.8758	0.6081	0.8758	0.9358
No log	9.9565	458	0.8769	0.6081	0.8769	0.9365
No log	10.0	460	0.8770	0.6081	0.8770	0.9365

Framework versions

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