ArabicNewSplits7_FineTuningAraBERT_run3_AugV5_k9_task3_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: 0.7793
• Qwk: 0.0953
• Mse: 0.7793
• Rmse: 0.8828

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: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.0769	2	3.6484	-0.0068	3.6484	1.9101
No log	0.1538	4	2.2368	-0.0496	2.2368	1.4956
No log	0.2308	6	1.3740	0.0016	1.3740	1.1722
No log	0.3077	8	1.0688	-0.1276	1.0688	1.0338
No log	0.3846	10	0.8674	-0.2238	0.8674	0.9314
No log	0.4615	12	0.7534	-0.0069	0.7534	0.8680
No log	0.5385	14	0.8214	-0.1233	0.8214	0.9063
No log	0.6154	16	1.0710	-0.0892	1.0710	1.0349
No log	0.6923	18	0.9421	-0.0459	0.9421	0.9706
No log	0.7692	20	0.8311	0.0670	0.8311	0.9117
No log	0.8462	22	0.9057	-0.0474	0.9057	0.9517
No log	0.9231	24	0.8799	0.0642	0.8799	0.9380
No log	1.0	26	0.8703	0.0157	0.8703	0.9329
No log	1.0769	28	0.8515	-0.0163	0.8515	0.9227
No log	1.1538	30	0.8824	0.0017	0.8824	0.9394
No log	1.2308	32	0.8780	0.0909	0.8780	0.9370
No log	1.3077	34	0.9661	0.0287	0.9661	0.9829
No log	1.3846	36	0.7051	0.0857	0.7051	0.8397
No log	1.4615	38	0.7020	0.0555	0.7020	0.8378
No log	1.5385	40	0.7422	-0.0188	0.7422	0.8615
No log	1.6154	42	0.8992	-0.0878	0.8992	0.9483
No log	1.6923	44	1.2600	0.0098	1.2600	1.1225
No log	1.7692	46	1.5706	0.0252	1.5706	1.2532
No log	1.8462	48	1.3789	0.0130	1.3789	1.1743
No log	1.9231	50	0.9283	-0.1660	0.9283	0.9635
No log	2.0	52	0.8285	-0.0790	0.8285	0.9102
No log	2.0769	54	0.8089	-0.0753	0.8089	0.8994
No log	2.1538	56	0.9125	-0.1676	0.9125	0.9552
No log	2.2308	58	1.0382	-0.0163	1.0382	1.0189
No log	2.3077	60	0.9793	-0.2080	0.9793	0.9896
No log	2.3846	62	0.8677	-0.0739	0.8677	0.9315
No log	2.4615	64	0.9150	-0.2184	0.9150	0.9566
No log	2.5385	66	1.1443	-0.2380	1.1443	1.0697
No log	2.6154	68	1.6756	-0.0654	1.6756	1.2944
No log	2.6923	70	1.8311	-0.0256	1.8311	1.3532
No log	2.7692	72	1.5137	0.0379	1.5137	1.2303
No log	2.8462	74	1.1504	0.0329	1.1504	1.0726
No log	2.9231	76	0.9269	0.0786	0.9269	0.9628
No log	3.0	78	0.8579	0.0456	0.8579	0.9262
No log	3.0769	80	0.9178	0.0727	0.9178	0.9580
No log	3.1538	82	1.2418	-0.0579	1.2418	1.1144
No log	3.2308	84	1.9538	0.0161	1.9538	1.3978
No log	3.3077	86	1.7908	0.0650	1.7908	1.3382
No log	3.3846	88	1.0905	-0.0579	1.0905	1.0443
No log	3.4615	90	0.9571	-0.0878	0.9571	0.9783
No log	3.5385	92	1.0591	-0.1734	1.0591	1.0291
No log	3.6154	94	1.0370	-0.1734	1.0370	1.0183
No log	3.6923	96	1.1296	-0.0353	1.1296	1.0628
No log	3.7692	98	1.4777	0.0636	1.4777	1.2156
No log	3.8462	100	1.4557	0.0112	1.4557	1.2065
No log	3.9231	102	1.1063	-0.0320	1.1063	1.0518
No log	4.0	104	0.8089	-0.1168	0.8089	0.8994
No log	4.0769	106	0.8386	-0.1074	0.8386	0.9158
No log	4.1538	108	0.8194	-0.1143	0.8194	0.9052
No log	4.2308	110	0.8139	0.0555	0.8139	0.9022
No log	4.3077	112	0.8879	-0.1246	0.8879	0.9423
No log	4.3846	114	1.0455	-0.1279	1.0455	1.0225
No log	4.4615	116	1.1435	-0.1281	1.1435	1.0693
No log	4.5385	118	1.1695	-0.0883	1.1695	1.0814
No log	4.6154	120	1.0661	-0.1111	1.0661	1.0325
No log	4.6923	122	0.9947	-0.1450	0.9947	0.9973
No log	4.7692	124	1.0715	-0.1437	1.0715	1.0351
No log	4.8462	126	1.3144	-0.1081	1.3144	1.1465
No log	4.9231	128	1.4809	-0.0276	1.4809	1.2169
No log	5.0	130	1.4468	-0.0507	1.4468	1.2028
No log	5.0769	132	1.2938	-0.0785	1.2938	1.1374
No log	5.1538	134	1.1090	-0.0409	1.1090	1.0531
No log	5.2308	136	1.0057	-0.0378	1.0057	1.0029
No log	5.3077	138	0.9849	-0.1152	0.9849	0.9924
No log	5.3846	140	0.9668	-0.1994	0.9668	0.9833
No log	5.4615	142	1.0603	-0.1088	1.0603	1.0297
No log	5.5385	144	1.2666	-0.1144	1.2666	1.1254
No log	5.6154	146	1.3106	-0.0820	1.3106	1.1448
No log	5.6923	148	1.2392	-0.0815	1.2392	1.1132
No log	5.7692	150	1.1176	-0.1549	1.1176	1.0572
No log	5.8462	152	1.1116	-0.1264	1.1116	1.0543
No log	5.9231	154	1.1574	-0.0578	1.1574	1.0758
No log	6.0	156	1.2118	-0.0721	1.2118	1.1008
No log	6.0769	158	1.2537	-0.0137	1.2537	1.1197
No log	6.1538	160	1.1032	-0.0991	1.1032	1.0503
No log	6.2308	162	0.9735	0.0045	0.9735	0.9866
No log	6.3077	164	0.9498	0.0151	0.9498	0.9746
No log	6.3846	166	0.9695	-0.1007	0.9695	0.9846
No log	6.4615	168	0.9538	-0.0349	0.9538	0.9766
No log	6.5385	170	0.9771	0.0336	0.9771	0.9885
No log	6.6154	172	1.0017	0.0014	1.0017	1.0009
No log	6.6923	174	1.0377	-0.0569	1.0377	1.0187
No log	6.7692	176	1.0493	-0.0910	1.0493	1.0243
No log	6.8462	178	1.0532	-0.1710	1.0532	1.0263
No log	6.9231	180	0.9823	-0.2190	0.9823	0.9911
No log	7.0	182	1.0766	-0.0786	1.0766	1.0376
No log	7.0769	184	1.2588	-0.0154	1.2588	1.1220
No log	7.1538	186	1.4028	0.1300	1.4028	1.1844
No log	7.2308	188	1.4855	0.1458	1.4855	1.2188
No log	7.3077	190	1.3607	0.2080	1.3607	1.1665
No log	7.3846	192	1.0915	0.0470	1.0915	1.0447
No log	7.4615	194	0.8733	-0.0241	0.8733	0.9345
No log	7.5385	196	0.9018	0.0426	0.9018	0.9496
No log	7.6154	198	0.9356	-0.1072	0.9356	0.9672
No log	7.6923	200	0.8815	-0.0027	0.8815	0.9389
No log	7.7692	202	0.8211	-0.0767	0.8211	0.9062
No log	7.8462	204	0.8286	-0.0425	0.8286	0.9102
No log	7.9231	206	0.9222	0.0526	0.9222	0.9603
No log	8.0	208	0.8149	-0.0251	0.8149	0.9027
No log	8.0769	210	0.8127	-0.0630	0.8127	0.9015
No log	8.1538	212	0.7926	-0.0630	0.7926	0.8903
No log	8.2308	214	0.7854	-0.0541	0.7854	0.8862
No log	8.3077	216	0.8140	-0.0524	0.8140	0.9022
No log	8.3846	218	0.8509	0.0509	0.8509	0.9225
No log	8.4615	220	0.9035	0.1036	0.9035	0.9505
No log	8.5385	222	0.8527	-0.0887	0.8527	0.9234
No log	8.6154	224	0.9005	-0.0164	0.9005	0.9489
No log	8.6923	226	0.9728	-0.1149	0.9728	0.9863
No log	8.7692	228	0.9705	-0.0166	0.9705	0.9852
No log	8.8462	230	0.9105	-0.0280	0.9105	0.9542
No log	8.9231	232	0.8550	0.0456	0.8550	0.9247
No log	9.0	234	0.9733	0.0642	0.9733	0.9866
No log	9.0769	236	0.8387	0.0786	0.8387	0.9158
No log	9.1538	238	0.7288	0.0874	0.7288	0.8537
No log	9.2308	240	0.7577	0.1413	0.7577	0.8705
No log	9.3077	242	0.7874	0.1404	0.7874	0.8873
No log	9.3846	244	0.8721	-0.0322	0.8721	0.9338
No log	9.4615	246	0.9412	-0.0054	0.9412	0.9702
No log	9.5385	248	0.8839	0.0541	0.8839	0.9401
No log	9.6154	250	0.9437	0.1149	0.9437	0.9714
No log	9.6923	252	1.1286	0.0342	1.1286	1.0623
No log	9.7692	254	1.0655	-0.0269	1.0655	1.0322
No log	9.8462	256	0.9615	0.0134	0.9615	0.9806
No log	9.9231	258	0.7527	0.0183	0.7527	0.8676
No log	10.0	260	0.7266	0.0085	0.7266	0.8524
No log	10.0769	262	0.7208	0.0821	0.7208	0.8490
No log	10.1538	264	0.7363	0.1304	0.7363	0.8581
No log	10.2308	266	0.7548	0.0922	0.7548	0.8688
No log	10.3077	268	0.8211	0.0639	0.8211	0.9061
No log	10.3846	270	0.8416	0.1094	0.8416	0.9174
No log	10.4615	272	0.8467	0.0101	0.8467	0.9202
No log	10.5385	274	0.8389	0.0840	0.8389	0.9159
No log	10.6154	276	0.8380	0.0200	0.8380	0.9154
No log	10.6923	278	0.7986	0.0481	0.7986	0.8937
No log	10.7692	280	0.7731	0.0840	0.7731	0.8793
No log	10.8462	282	0.7564	0.1080	0.7564	0.8697
No log	10.9231	284	0.7478	0.0598	0.7478	0.8647
No log	11.0	286	0.8736	-0.0852	0.8736	0.9347
No log	11.0769	288	0.8924	-0.0852	0.8924	0.9447
No log	11.1538	290	0.8530	-0.0173	0.8530	0.9236
No log	11.2308	292	0.8612	-0.0132	0.8612	0.9280
No log	11.3077	294	1.1743	0.0089	1.1743	1.0837
No log	11.3846	296	1.2871	-0.0077	1.2871	1.1345
No log	11.4615	298	0.9751	-0.0143	0.9751	0.9875
No log	11.5385	300	0.8245	0.1093	0.8245	0.9080
No log	11.6154	302	0.8322	-0.0049	0.8322	0.9123
No log	11.6923	304	0.8703	-0.0602	0.8703	0.9329
No log	11.7692	306	0.9158	-0.1013	0.9158	0.9570
No log	11.8462	308	0.9470	-0.1135	0.9470	0.9731
No log	11.9231	310	1.0229	-0.0545	1.0229	1.0114
No log	12.0	312	1.0038	-0.0163	1.0038	1.0019
No log	12.0769	314	0.8801	-0.0790	0.8801	0.9381
No log	12.1538	316	0.8539	-0.1747	0.8539	0.9241
No log	12.2308	318	0.8606	-0.1230	0.8606	0.9277
No log	12.3077	320	0.8967	-0.1747	0.8967	0.9469
No log	12.3846	322	0.9852	-0.2121	0.9852	0.9926
No log	12.4615	324	1.0143	-0.2136	1.0143	1.0071
No log	12.5385	326	1.0716	-0.1660	1.0716	1.0352
No log	12.6154	328	0.9861	-0.0767	0.9861	0.9930
No log	12.6923	330	0.9253	-0.0573	0.9253	0.9619
No log	12.7692	332	0.9599	-0.1259	0.9599	0.9797
No log	12.8462	334	0.9329	-0.0852	0.9329	0.9659
No log	12.9231	336	1.0095	-0.0916	1.0095	1.0047
No log	13.0	338	1.0818	-0.0345	1.0818	1.0401
No log	13.0769	340	0.9291	-0.0504	0.9291	0.9639
No log	13.1538	342	0.7734	0.0225	0.7734	0.8794
No log	13.2308	344	0.7875	0.0089	0.7875	0.8874
No log	13.3077	346	0.7697	-0.0427	0.7697	0.8773
No log	13.3846	348	0.8405	0.0346	0.8405	0.9168
No log	13.4615	350	1.0881	0.1008	1.0881	1.0431
No log	13.5385	352	1.0916	0.0006	1.0916	1.0448
No log	13.6154	354	0.8540	0.1150	0.8540	0.9241
No log	13.6923	356	0.7771	0.0191	0.7771	0.8815
No log	13.7692	358	0.7941	0.0159	0.7941	0.8911
No log	13.8462	360	0.8255	0.0442	0.8255	0.9086
No log	13.9231	362	0.8718	-0.0008	0.8718	0.9337
No log	14.0	364	0.8841	-0.0008	0.8841	0.9402
No log	14.0769	366	0.8633	0.0043	0.8633	0.9291
No log	14.1538	368	0.8162	-0.0240	0.8162	0.9034
No log	14.2308	370	0.8280	-0.1604	0.8280	0.9100
No log	14.3077	372	0.9354	0.0909	0.9354	0.9672
No log	14.3846	374	1.1028	-0.0586	1.1028	1.0502
No log	14.4615	376	1.2344	-0.0931	1.2344	1.1111
No log	14.5385	378	1.1022	-0.0606	1.1022	1.0498
No log	14.6154	380	0.8460	-0.0287	0.8460	0.9198
No log	14.6923	382	0.8509	-0.0692	0.8509	0.9225
No log	14.7692	384	0.8673	-0.0648	0.8673	0.9313
No log	14.8462	386	0.8409	-0.0179	0.8409	0.9170
No log	14.9231	388	0.9296	-0.0425	0.9296	0.9641
No log	15.0	390	0.9709	0.0260	0.9709	0.9853
No log	15.0769	392	0.9083	0.1291	0.9083	0.9530
No log	15.1538	394	0.8626	0.0071	0.8626	0.9288
No log	15.2308	396	0.8014	-0.0170	0.8014	0.8952
No log	15.3077	398	0.8105	0.1395	0.8105	0.9003
No log	15.3846	400	0.7830	0.0999	0.7830	0.8849
No log	15.4615	402	0.7574	-0.0739	0.7574	0.8703
No log	15.5385	404	0.8008	0.0549	0.8008	0.8949
No log	15.6154	406	0.7940	-0.0766	0.7940	0.8911
No log	15.6923	408	0.7715	-0.0766	0.7715	0.8783
No log	15.7692	410	0.7631	0.0479	0.7631	0.8736
No log	15.8462	412	0.7647	-0.0096	0.7647	0.8745
No log	15.9231	414	0.8058	0.0099	0.8058	0.8977
No log	16.0	416	0.7663	-0.0731	0.7663	0.8754
No log	16.0769	418	0.7475	-0.0118	0.7475	0.8646
No log	16.1538	420	0.7599	0.0571	0.7599	0.8717
No log	16.2308	422	0.8182	-0.0989	0.8182	0.9045
No log	16.3077	424	0.8028	-0.0786	0.8028	0.8960
No log	16.3846	426	0.7708	0.0334	0.7708	0.8779
No log	16.4615	428	0.8511	0.0442	0.8511	0.9226
No log	16.5385	430	0.8739	0.0346	0.8739	0.9348
No log	16.6154	432	0.8049	0.0026	0.8049	0.8971
No log	16.6923	434	0.8286	-0.0093	0.8286	0.9103
No log	16.7692	436	0.8000	0.0673	0.8000	0.8944
No log	16.8462	438	0.7562	-0.0567	0.7562	0.8696
No log	16.9231	440	0.8021	0.0913	0.8021	0.8956
No log	17.0	442	0.8725	0.0642	0.8725	0.9341
No log	17.0769	444	1.0385	-0.0013	1.0385	1.0191
No log	17.1538	446	0.9178	0.1114	0.9178	0.9580
No log	17.2308	448	0.7188	0.0296	0.7188	0.8478
No log	17.3077	450	0.7335	-0.0363	0.7335	0.8564
No log	17.3846	452	0.8810	0.0789	0.8810	0.9386
No log	17.4615	454	0.8715	0.0794	0.8715	0.9335
No log	17.5385	456	0.7397	0.0122	0.7397	0.8600
No log	17.6154	458	0.7980	0.0909	0.7980	0.8933
No log	17.6923	460	1.0354	-0.0269	1.0354	1.0176
No log	17.7692	462	1.0598	0.0046	1.0598	1.0295
No log	17.8462	464	0.9356	0.0873	0.9356	0.9673
No log	17.9231	466	0.8072	0.0959	0.8072	0.8985
No log	18.0	468	0.7606	0.1095	0.7606	0.8721
No log	18.0769	470	0.7792	0.2498	0.7792	0.8827
No log	18.1538	472	0.8311	0.2491	0.8311	0.9117
No log	18.2308	474	0.9466	0.1402	0.9466	0.9730
No log	18.3077	476	0.9875	0.1402	0.9875	0.9937
No log	18.3846	478	0.8289	0.1825	0.8289	0.9104
No log	18.4615	480	0.7718	0.0670	0.7718	0.8785
No log	18.5385	482	0.7829	0.0588	0.7829	0.8848
No log	18.6154	484	0.8485	0.2370	0.8485	0.9211
No log	18.6923	486	0.9024	0.1525	0.9024	0.9499
No log	18.7692	488	0.9484	0.1442	0.9484	0.9739
No log	18.8462	490	0.8905	0.1269	0.8905	0.9437
No log	18.9231	492	0.7794	0.1107	0.7794	0.8828
No log	19.0	494	0.7818	0.1106	0.7818	0.8842
No log	19.0769	496	0.8194	0.1453	0.8194	0.9052
No log	19.1538	498	0.9391	0.1024	0.9391	0.9691
0.3306	19.2308	500	1.0868	0.1363	1.0868	1.0425
0.3306	19.3077	502	1.0054	0.0545	1.0054	1.0027
0.3306	19.3846	504	0.9329	0.0182	0.9329	0.9659
0.3306	19.4615	506	0.8749	0.0260	0.8749	0.9354
0.3306	19.5385	508	0.8190	0.2077	0.8190	0.9050
0.3306	19.6154	510	0.8148	0.1716	0.8148	0.9027
0.3306	19.6923	512	0.8629	0.1024	0.8629	0.9289
0.3306	19.7692	514	0.8676	0.0233	0.8676	0.9314
0.3306	19.8462	516	0.8186	0.1064	0.8186	0.9047
0.3306	19.9231	518	0.7618	0.0512	0.7618	0.8728
0.3306	20.0	520	0.7793	0.0953	0.7793	0.8828

Framework versions

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