ArabicNewSplits6_FineTuningAraBERT_run1_AugV5_k12_task5_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: 1.0017
• Qwk: 0.6118
• Mse: 1.0017
• Rmse: 1.0008

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	2.6343	-0.0023	2.6343	1.6230
No log	0.0870	4	1.9071	0.0319	1.9071	1.3810
No log	0.1304	6	1.3330	0.2457	1.3330	1.1545
No log	0.1739	8	1.5848	0.0731	1.5848	1.2589
No log	0.2174	10	1.6723	0.1350	1.6723	1.2932
No log	0.2609	12	1.6348	0.1205	1.6348	1.2786
No log	0.3043	14	1.5169	0.1449	1.5169	1.2316
No log	0.3478	16	1.4132	0.2119	1.4132	1.1888
No log	0.3913	18	1.3751	0.2047	1.3751	1.1727
No log	0.4348	20	1.5382	0.2934	1.5382	1.2402
No log	0.4783	22	1.6814	0.3288	1.6814	1.2967
No log	0.5217	24	1.5474	0.3448	1.5474	1.2440
No log	0.5652	26	1.3368	0.3299	1.3368	1.1562
No log	0.6087	28	1.2498	0.2087	1.2498	1.1179
No log	0.6522	30	1.2237	0.2574	1.2237	1.1062
No log	0.6957	32	1.1837	0.2991	1.1837	1.0880
No log	0.7391	34	1.1779	0.3319	1.1779	1.0853
No log	0.7826	36	1.1731	0.3271	1.1731	1.0831
No log	0.8261	38	1.1784	0.2984	1.1784	1.0855
No log	0.8696	40	1.3366	0.4204	1.3366	1.1561
No log	0.9130	42	1.5053	0.3490	1.5053	1.2269
No log	0.9565	44	1.5329	0.2578	1.5329	1.2381
No log	1.0	46	1.4395	0.2616	1.4395	1.1998
No log	1.0435	48	1.3583	0.3873	1.3583	1.1655
No log	1.0870	50	1.1998	0.4106	1.1998	1.0954
No log	1.1304	52	1.0725	0.4209	1.0725	1.0356
No log	1.1739	54	1.0921	0.4109	1.0921	1.0450
No log	1.2174	56	1.1455	0.4174	1.1455	1.0703
No log	1.2609	58	1.1643	0.4310	1.1643	1.0790
No log	1.3043	60	1.1335	0.4310	1.1335	1.0647
No log	1.3478	62	1.0375	0.4275	1.0375	1.0186
No log	1.3913	64	0.9800	0.4847	0.9800	0.9899
No log	1.4348	66	1.0441	0.5041	1.0441	1.0218
No log	1.4783	68	1.1818	0.4739	1.1818	1.0871
No log	1.5217	70	1.2031	0.4626	1.2031	1.0969
No log	1.5652	72	1.2234	0.4321	1.2234	1.1061
No log	1.6087	74	1.1554	0.4841	1.1554	1.0749
No log	1.6522	76	1.0766	0.4545	1.0766	1.0376
No log	1.6957	78	1.0497	0.4617	1.0497	1.0246
No log	1.7391	80	1.0450	0.4922	1.0450	1.0223
No log	1.7826	82	1.0629	0.5178	1.0629	1.0310
No log	1.8261	84	1.0588	0.4867	1.0588	1.0290
No log	1.8696	86	1.1203	0.4686	1.1203	1.0585
No log	1.9130	88	1.1615	0.4762	1.1615	1.0777
No log	1.9565	90	1.1543	0.4888	1.1543	1.0744
No log	2.0	92	1.1483	0.4374	1.1483	1.0716
No log	2.0435	94	1.1472	0.3892	1.1472	1.0711
No log	2.0870	96	1.1343	0.3892	1.1343	1.0650
No log	2.1304	98	1.1101	0.4612	1.1101	1.0536
No log	2.1739	100	1.0591	0.5313	1.0591	1.0291
No log	2.2174	102	1.0286	0.5162	1.0286	1.0142
No log	2.2609	104	0.9748	0.5280	0.9748	0.9873
No log	2.3043	106	0.9561	0.5386	0.9561	0.9778
No log	2.3478	108	0.9149	0.5656	0.9149	0.9565
No log	2.3913	110	0.9026	0.5765	0.9026	0.9501
No log	2.4348	112	0.8983	0.5711	0.8983	0.9478
No log	2.4783	114	0.9456	0.5961	0.9456	0.9724
No log	2.5217	116	1.1052	0.5421	1.1052	1.0513
No log	2.5652	118	1.1915	0.5205	1.1915	1.0916
No log	2.6087	120	1.2662	0.5327	1.2662	1.1253
No log	2.6522	122	1.3058	0.5394	1.3058	1.1427
No log	2.6957	124	1.3581	0.5541	1.3581	1.1654
No log	2.7391	126	1.1937	0.5544	1.1937	1.0926
No log	2.7826	128	1.1089	0.5523	1.1089	1.0530
No log	2.8261	130	1.0750	0.5331	1.0750	1.0368
No log	2.8696	132	1.1430	0.5564	1.1430	1.0691
No log	2.9130	134	1.1607	0.5485	1.1607	1.0774
No log	2.9565	136	1.1974	0.5520	1.1974	1.0943
No log	3.0	138	1.3035	0.5475	1.3035	1.1417
No log	3.0435	140	1.4987	0.5409	1.4987	1.2242
No log	3.0870	142	1.5221	0.5185	1.5221	1.2337
No log	3.1304	144	1.4033	0.5321	1.4033	1.1846
No log	3.1739	146	1.2258	0.5293	1.2258	1.1071
No log	3.2174	148	1.2458	0.5365	1.2458	1.1162
No log	3.2609	150	1.2477	0.5220	1.2477	1.1170
No log	3.3043	152	1.1396	0.5439	1.1396	1.0675
No log	3.3478	154	0.9846	0.5907	0.9846	0.9923
No log	3.3913	156	0.9126	0.6535	0.9126	0.9553
No log	3.4348	158	0.9217	0.6148	0.9217	0.9600
No log	3.4783	160	1.0141	0.6289	1.0141	1.0070
No log	3.5217	162	1.1707	0.5827	1.1707	1.0820
No log	3.5652	164	1.2505	0.5835	1.2505	1.1183
No log	3.6087	166	1.1556	0.5924	1.1556	1.0750
No log	3.6522	168	1.0462	0.6113	1.0462	1.0229
No log	3.6957	170	1.0780	0.6095	1.0780	1.0383
No log	3.7391	172	1.0647	0.5974	1.0647	1.0319
No log	3.7826	174	0.9915	0.6414	0.9915	0.9957
No log	3.8261	176	0.9114	0.6302	0.9114	0.9546
No log	3.8696	178	0.8766	0.6232	0.8766	0.9363
No log	3.9130	180	0.9117	0.6338	0.9117	0.9548
No log	3.9565	182	1.0319	0.5846	1.0319	1.0158
No log	4.0	184	1.0441	0.5913	1.0441	1.0218
No log	4.0435	186	0.9823	0.6055	0.9823	0.9911
No log	4.0870	188	0.9558	0.6168	0.9558	0.9776
No log	4.1304	190	0.9141	0.6410	0.9141	0.9561
No log	4.1739	192	0.9306	0.6474	0.9306	0.9647
No log	4.2174	194	0.9582	0.6421	0.9582	0.9789
No log	4.2609	196	0.9283	0.6332	0.9283	0.9635
No log	4.3043	198	0.9261	0.6348	0.9261	0.9624
No log	4.3478	200	0.9504	0.6364	0.9504	0.9749
No log	4.3913	202	0.9402	0.6312	0.9402	0.9696
No log	4.4348	204	0.9603	0.6165	0.9603	0.9800
No log	4.4783	206	1.0090	0.6015	1.0090	1.0045
No log	4.5217	208	1.0256	0.6034	1.0256	1.0127
No log	4.5652	210	1.0471	0.6021	1.0471	1.0233
No log	4.6087	212	0.9806	0.6362	0.9806	0.9902
No log	4.6522	214	0.8731	0.6715	0.8731	0.9344
No log	4.6957	216	0.8732	0.6600	0.8732	0.9345
No log	4.7391	218	0.9695	0.6179	0.9695	0.9847
No log	4.7826	220	1.0959	0.5765	1.0959	1.0469
No log	4.8261	222	1.2624	0.5679	1.2624	1.1235
No log	4.8696	224	1.2471	0.5601	1.2471	1.1168
No log	4.9130	226	1.1333	0.5869	1.1333	1.0646
No log	4.9565	228	1.0470	0.5961	1.0470	1.0232
No log	5.0	230	1.0332	0.5961	1.0332	1.0165
No log	5.0435	232	0.9842	0.5901	0.9842	0.9921
No log	5.0870	234	0.9795	0.6085	0.9795	0.9897
No log	5.1304	236	1.0627	0.5977	1.0627	1.0309
No log	5.1739	238	1.1373	0.6071	1.1373	1.0664
No log	5.2174	240	1.1370	0.5844	1.1370	1.0663
No log	5.2609	242	1.1170	0.6059	1.1170	1.0569
No log	5.3043	244	1.0821	0.6227	1.0821	1.0402
No log	5.3478	246	1.0233	0.6587	1.0233	1.0116
No log	5.3913	248	0.9085	0.6877	0.9085	0.9532
No log	5.4348	250	0.9015	0.6896	0.9015	0.9495
No log	5.4783	252	0.9811	0.6540	0.9811	0.9905
No log	5.5217	254	1.1389	0.6211	1.1389	1.0672
No log	5.5652	256	1.2743	0.5804	1.2743	1.1288
No log	5.6087	258	1.2705	0.5804	1.2705	1.1272
No log	5.6522	260	1.2029	0.5862	1.2029	1.0968
No log	5.6957	262	1.1438	0.5659	1.1438	1.0695
No log	5.7391	264	1.0615	0.5992	1.0615	1.0303
No log	5.7826	266	1.0956	0.5905	1.0956	1.0467
No log	5.8261	268	1.2409	0.5835	1.2409	1.1139
No log	5.8696	270	1.4355	0.5679	1.4355	1.1981
No log	5.9130	272	1.4562	0.5429	1.4562	1.2067
No log	5.9565	274	1.3131	0.5552	1.3131	1.1459
No log	6.0	276	1.1502	0.5692	1.1502	1.0725
No log	6.0435	278	1.0930	0.5302	1.0930	1.0455
No log	6.0870	280	1.0379	0.5636	1.0379	1.0188
No log	6.1304	282	1.0255	0.5861	1.0255	1.0127
No log	6.1739	284	1.0211	0.5970	1.0211	1.0105
No log	6.2174	286	0.9777	0.6156	0.9777	0.9888
No log	6.2609	288	0.9732	0.6295	0.9732	0.9865
No log	6.3043	290	1.0289	0.6028	1.0289	1.0143
No log	6.3478	292	1.0138	0.6280	1.0138	1.0069
No log	6.3913	294	0.9489	0.6354	0.9489	0.9741
No log	6.4348	296	0.9146	0.6449	0.9146	0.9563
No log	6.4783	298	0.8894	0.6543	0.8894	0.9431
No log	6.5217	300	0.9164	0.6449	0.9164	0.9573
No log	6.5652	302	1.0034	0.6275	1.0034	1.0017
No log	6.6087	304	1.1277	0.5919	1.1277	1.0619
No log	6.6522	306	1.1600	0.5836	1.1600	1.0770
No log	6.6957	308	1.1127	0.6010	1.1127	1.0549
No log	6.7391	310	1.0024	0.6174	1.0024	1.0012
No log	6.7826	312	0.8872	0.6356	0.8872	0.9419
No log	6.8261	314	0.8681	0.6371	0.8681	0.9317
No log	6.8696	316	0.9008	0.6310	0.9008	0.9491
No log	6.9130	318	0.9920	0.6172	0.9920	0.9960
No log	6.9565	320	1.0706	0.6138	1.0706	1.0347
No log	7.0	322	1.0602	0.6257	1.0602	1.0297
No log	7.0435	324	0.9928	0.6080	0.9928	0.9964
No log	7.0870	326	0.9652	0.6107	0.9652	0.9824
No log	7.1304	328	0.9718	0.6107	0.9718	0.9858
No log	7.1739	330	0.9604	0.6107	0.9604	0.9800
No log	7.2174	332	0.9542	0.6151	0.9542	0.9768
No log	7.2609	334	0.9804	0.6309	0.9804	0.9901
No log	7.3043	336	1.0306	0.6137	1.0306	1.0152
No log	7.3478	338	1.0801	0.6144	1.0801	1.0393
No log	7.3913	340	1.0620	0.6170	1.0620	1.0305
No log	7.4348	342	1.0208	0.6147	1.0208	1.0103
No log	7.4783	344	1.0539	0.6108	1.0539	1.0266
No log	7.5217	346	1.0854	0.6024	1.0854	1.0418
No log	7.5652	348	1.0713	0.6082	1.0713	1.0350
No log	7.6087	350	1.0196	0.6156	1.0196	1.0097
No log	7.6522	352	0.9942	0.6156	0.9942	0.9971
No log	7.6957	354	0.9870	0.6156	0.9870	0.9935
No log	7.7391	356	1.0232	0.6156	1.0232	1.0115
No log	7.7826	358	1.0485	0.6082	1.0485	1.0239
No log	7.8261	360	1.0829	0.6145	1.0829	1.0406
No log	7.8696	362	1.1572	0.5984	1.1572	1.0757
No log	7.9130	364	1.1866	0.6002	1.1866	1.0893
No log	7.9565	366	1.1462	0.6113	1.1462	1.0706
No log	8.0	368	1.0547	0.6128	1.0547	1.0270
No log	8.0435	370	0.9577	0.6446	0.9577	0.9786
No log	8.0870	372	0.9177	0.6385	0.9177	0.9580
No log	8.1304	374	0.9135	0.6385	0.9135	0.9558
No log	8.1739	376	0.9276	0.6290	0.9276	0.9631
No log	8.2174	378	0.9570	0.6446	0.9570	0.9783
No log	8.2609	380	0.9615	0.6446	0.9615	0.9806
No log	8.3043	382	0.9763	0.6508	0.9763	0.9881
No log	8.3478	384	0.9772	0.6446	0.9772	0.9886
No log	8.3913	386	0.9676	0.6446	0.9676	0.9837
No log	8.4348	388	0.9451	0.6449	0.9451	0.9721
No log	8.4783	390	0.9155	0.6385	0.9155	0.9568
No log	8.5217	392	0.8981	0.6482	0.8981	0.9477
No log	8.5652	394	0.9060	0.6385	0.9060	0.9518
No log	8.6087	396	0.9354	0.6385	0.9354	0.9672
No log	8.6522	398	0.9757	0.6387	0.9757	0.9878
No log	8.6957	400	1.0207	0.6334	1.0207	1.0103
No log	8.7391	402	1.0534	0.6231	1.0534	1.0263
No log	8.7826	404	1.0759	0.6232	1.0759	1.0372
No log	8.8261	406	1.0958	0.6178	1.0958	1.0468
No log	8.8696	408	1.0861	0.6178	1.0861	1.0422
No log	8.9130	410	1.0504	0.6291	1.0504	1.0249
No log	8.9565	412	1.0075	0.6196	1.0075	1.0037
No log	9.0	414	0.9860	0.6161	0.9860	0.9930
No log	9.0435	416	0.9560	0.6324	0.9560	0.9777
No log	9.0870	418	0.9200	0.6290	0.9200	0.9592
No log	9.1304	420	0.9063	0.6385	0.9063	0.9520
No log	9.1739	422	0.9121	0.6290	0.9121	0.9550
No log	9.2174	424	0.9226	0.6290	0.9226	0.9605
No log	9.2609	426	0.9337	0.6290	0.9337	0.9663
No log	9.3043	428	0.9573	0.6040	0.9573	0.9784
No log	9.3478	430	0.9801	0.6062	0.9801	0.9900
No log	9.3913	432	0.9955	0.6101	0.9955	0.9977
No log	9.4348	434	1.0141	0.6075	1.0141	1.0070
No log	9.4783	436	1.0324	0.6172	1.0324	1.0161
No log	9.5217	438	1.0415	0.6221	1.0415	1.0206
No log	9.5652	440	1.0512	0.6221	1.0512	1.0253
No log	9.6087	442	1.0560	0.6221	1.0560	1.0276
No log	9.6522	444	1.0523	0.6221	1.0523	1.0258
No log	9.6957	446	1.0440	0.6221	1.0440	1.0218
No log	9.7391	448	1.0322	0.6125	1.0322	1.0160
No log	9.7826	450	1.0222	0.6138	1.0222	1.0110
No log	9.8261	452	1.0127	0.6138	1.0127	1.0063
No log	9.8696	454	1.0082	0.6105	1.0082	1.0041
No log	9.9130	456	1.0052	0.6118	1.0052	1.0026
No log	9.9565	458	1.0029	0.6118	1.0029	1.0014
No log	10.0	460	1.0017	0.6118	1.0017	1.0008

Framework versions

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