ArabicNewSplits7_FineTuningAraBERT_run2_AugV5_k16_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: 0.8279
• Qwk: -0.1208
• Mse: 0.8279
• Rmse: 0.9099

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	0.0465	2	3.7246	-0.0068	3.7246	1.9299
No log	0.0930	4	2.0014	0.0304	2.0014	1.4147
No log	0.1395	6	1.8875	0.0372	1.8875	1.3739
No log	0.1860	8	1.6258	-0.0702	1.6258	1.2751
No log	0.2326	10	0.9176	-0.1688	0.9176	0.9579
No log	0.2791	12	0.7535	-0.1236	0.7535	0.8680
No log	0.3256	14	0.9002	0.0026	0.9002	0.9488
No log	0.3721	16	1.1537	0.0279	1.1537	1.0741
No log	0.4186	18	1.3957	0.0	1.3957	1.1814
No log	0.4651	20	1.3179	0.0	1.3179	1.1480
No log	0.5116	22	1.0646	-0.0234	1.0646	1.0318
No log	0.5581	24	0.9999	-0.0695	0.9999	0.9999
No log	0.6047	26	0.9609	-0.0686	0.9609	0.9803
No log	0.6512	28	1.0698	-0.0234	1.0698	1.0343
No log	0.6977	30	0.9765	0.0083	0.9765	0.9882
No log	0.7442	32	1.0029	-0.0221	1.0029	1.0014
No log	0.7907	34	1.1231	-0.0234	1.1231	1.0598
No log	0.8372	36	1.0281	-0.0468	1.0281	1.0140
No log	0.8837	38	0.9512	-0.0372	0.9512	0.9753
No log	0.9302	40	0.7967	-0.0766	0.7967	0.8926
No log	0.9767	42	0.7191	0.0	0.7191	0.8480
No log	1.0233	44	0.7244	0.0	0.7244	0.8511
No log	1.0698	46	0.7943	-0.0739	0.7943	0.8912
No log	1.1163	48	0.8178	-0.1241	0.8178	0.9043
No log	1.1628	50	0.7800	-0.0679	0.7800	0.8832
No log	1.2093	52	0.8207	-0.1233	0.8207	0.9059
No log	1.2558	54	1.0522	-0.0359	1.0522	1.0258
No log	1.3023	56	1.0617	-0.1612	1.0617	1.0304
No log	1.3488	58	0.9348	-0.0878	0.9348	0.9669
No log	1.3953	60	0.8498	-0.1244	0.8498	0.9218
No log	1.4419	62	0.7397	0.0555	0.7397	0.8601
No log	1.4884	64	0.7083	0.0555	0.7083	0.8416
No log	1.5349	66	0.7603	-0.0069	0.7603	0.8719
No log	1.5814	68	1.1729	-0.0720	1.1729	1.0830
No log	1.6279	70	1.6100	0.0032	1.6100	1.2688
No log	1.6744	72	1.6553	0.0279	1.6553	1.2866
No log	1.7209	74	1.3505	0.0083	1.3505	1.1621
No log	1.7674	76	0.9283	-0.0902	0.9283	0.9635
No log	1.8140	78	0.7689	0.0374	0.7689	0.8769
No log	1.8605	80	0.7334	-0.0069	0.7334	0.8564
No log	1.9070	82	0.7383	-0.0069	0.7383	0.8592
No log	1.9535	84	0.9505	0.0793	0.9505	0.9749
No log	2.0	86	1.4526	-0.0433	1.4526	1.2052
No log	2.0465	88	1.4940	-0.0422	1.4940	1.2223
No log	2.0930	90	1.0408	0.1399	1.0408	1.0202
No log	2.1395	92	0.8014	0.0759	0.8014	0.8952
No log	2.1860	94	0.8662	-0.0331	0.8662	0.9307
No log	2.2326	96	1.1525	0.0147	1.1525	1.0736
No log	2.2791	98	1.3606	0.0585	1.3606	1.1665
No log	2.3256	100	1.0859	-0.0500	1.0859	1.0420
No log	2.3721	102	0.7759	0.0918	0.7759	0.8809
No log	2.4186	104	0.8421	-0.1538	0.8421	0.9177
No log	2.4651	106	0.8419	-0.0633	0.8419	0.9175
No log	2.5116	108	0.9000	-0.1152	0.9000	0.9487
No log	2.5581	110	1.2257	0.0305	1.2257	1.1071
No log	2.6047	112	0.9679	-0.0878	0.9679	0.9838
No log	2.6512	114	0.7820	-0.1001	0.7820	0.8843
No log	2.6977	116	0.8290	-0.0939	0.8290	0.9105
No log	2.7442	118	0.7710	-0.0499	0.7710	0.8781
No log	2.7907	120	0.9497	0.0287	0.9497	0.9745
No log	2.8372	122	0.9878	-0.0079	0.9878	0.9939
No log	2.8837	124	0.7628	0.0	0.7628	0.8734
No log	2.9302	126	0.7509	-0.0571	0.7509	0.8666
No log	2.9767	128	0.7575	-0.0152	0.7575	0.8703
No log	3.0233	130	0.8902	0.0456	0.8902	0.9435
No log	3.0698	132	0.7503	-0.0179	0.7503	0.8662
No log	3.1163	134	0.7393	-0.0152	0.7393	0.8598
No log	3.1628	136	0.7952	0.0999	0.7952	0.8917
No log	3.2093	138	0.7850	0.0588	0.7850	0.8860
No log	3.2558	140	0.7664	0.0814	0.7664	0.8755
No log	3.3023	142	0.8017	0.0338	0.8017	0.8954
No log	3.3488	144	1.1191	-0.0571	1.1191	1.0579
No log	3.3953	146	1.2454	0.0945	1.2454	1.1160
No log	3.4419	148	0.9082	-0.1734	0.9082	0.9530
No log	3.4884	150	0.9588	-0.0616	0.9588	0.9792
No log	3.5349	152	0.9024	-0.0771	0.9024	0.9499
No log	3.5814	154	0.8917	0.0226	0.8917	0.9443
No log	3.6279	156	1.0235	-0.1107	1.0235	1.0117
No log	3.6744	158	0.8577	0.0393	0.8577	0.9261
No log	3.7209	160	0.8574	0.0172	0.8574	0.9259
No log	3.7674	162	0.8423	0.0410	0.8423	0.9178
No log	3.8140	164	0.8512	-0.0156	0.8512	0.9226
No log	3.8605	166	0.8479	0.0257	0.8479	0.9208
No log	3.9070	168	0.8372	-0.0389	0.8372	0.9150
No log	3.9535	170	0.8629	-0.0268	0.8629	0.9289
No log	4.0	172	0.9164	-0.0241	0.9164	0.9573
No log	4.0465	174	0.9051	-0.0230	0.9051	0.9514
No log	4.0930	176	0.8203	0.1287	0.8203	0.9057
No log	4.1395	178	0.9090	-0.1245	0.9090	0.9534
No log	4.1860	180	0.8735	-0.0934	0.8735	0.9346
No log	4.2326	182	0.8048	0.1144	0.8048	0.8971
No log	4.2791	184	0.8280	0.0438	0.8280	0.9099
No log	4.3256	186	0.8129	0.0187	0.8129	0.9016
No log	4.3721	188	0.8465	-0.0166	0.8465	0.9201
No log	4.4186	190	0.7759	0.0610	0.7759	0.8809
No log	4.4651	192	0.7429	0.0528	0.7429	0.8619
No log	4.5116	194	0.7362	-0.0033	0.7362	0.8580
No log	4.5581	196	0.7765	0.0122	0.7765	0.8812
No log	4.6047	198	0.8206	-0.0271	0.8206	0.9058
No log	4.6512	200	0.8363	-0.0705	0.8363	0.9145
No log	4.6977	202	0.8022	0.0031	0.8022	0.8957
No log	4.7442	204	0.8204	-0.0329	0.8204	0.9058
No log	4.7907	206	0.9326	-0.1245	0.9326	0.9657
No log	4.8372	208	0.8808	-0.1474	0.8808	0.9385
No log	4.8837	210	0.8207	-0.0473	0.8207	0.9059
No log	4.9302	212	0.8341	-0.0690	0.8341	0.9133
No log	4.9767	214	0.8309	-0.1616	0.8309	0.9115
No log	5.0233	216	0.8954	-0.1474	0.8954	0.9462
No log	5.0698	218	0.9409	-0.0442	0.9409	0.9700
No log	5.1163	220	0.8572	-0.2224	0.8572	0.9258
No log	5.1628	222	0.8919	-0.0209	0.8919	0.9444
No log	5.2093	224	1.0035	-0.1162	1.0035	1.0017
No log	5.2558	226	0.8632	-0.0921	0.8632	0.9291
No log	5.3023	228	0.9342	-0.0722	0.9342	0.9666
No log	5.3488	230	0.9475	-0.0685	0.9475	0.9734
No log	5.3953	232	0.8389	-0.1823	0.8389	0.9159
No log	5.4419	234	0.9965	-0.0471	0.9965	0.9982
No log	5.4884	236	1.2440	-0.0301	1.2440	1.1154
No log	5.5349	238	0.9638	-0.0809	0.9638	0.9817
No log	5.5814	240	0.8400	-0.1833	0.8400	0.9165
No log	5.6279	242	0.9103	-0.1298	0.9103	0.9541
No log	5.6744	244	0.8528	-0.1399	0.8528	0.9234
No log	5.7209	246	0.8082	-0.0578	0.8082	0.8990
No log	5.7674	248	0.9322	-0.0033	0.9322	0.9655
No log	5.8140	250	0.9949	-0.0571	0.9949	0.9975
No log	5.8605	252	0.8197	0.0191	0.8197	0.9053
No log	5.9070	254	0.7556	0.0416	0.7556	0.8692
No log	5.9535	256	0.7658	0.0374	0.7658	0.8751
No log	6.0	258	0.7858	-0.1542	0.7858	0.8865
No log	6.0465	260	0.8293	-0.0750	0.8293	0.9107
No log	6.0930	262	0.8284	-0.0408	0.8284	0.9102
No log	6.1395	264	0.8504	-0.0339	0.8504	0.9222
No log	6.1860	266	0.8302	0.0049	0.8302	0.9111
No log	6.2326	268	0.8248	0.0074	0.8248	0.9082
No log	6.2791	270	0.8109	0.1196	0.8109	0.9005
No log	6.3256	272	0.8704	0.1196	0.8704	0.9330
No log	6.3721	274	0.8635	0.0748	0.8635	0.9292
No log	6.4186	276	0.7870	0.0225	0.7870	0.8871
No log	6.4651	278	0.7753	0.0395	0.7753	0.8805
No log	6.5116	280	0.7954	-0.0091	0.7954	0.8919
No log	6.5581	282	0.8408	-0.0370	0.8408	0.9170
No log	6.6047	284	0.8769	-0.0705	0.8769	0.9364
No log	6.6512	286	0.9092	-0.0508	0.9092	0.9535
No log	6.6977	288	0.9940	-0.1372	0.9940	0.9970
No log	6.7442	290	0.9552	-0.1064	0.9552	0.9773
No log	6.7907	292	0.8797	-0.0647	0.8797	0.9379
No log	6.8372	294	0.8742	-0.0578	0.8742	0.9350
No log	6.8837	296	0.8932	0.0470	0.8932	0.9451
No log	6.9302	298	0.8736	0.0017	0.8736	0.9347
No log	6.9767	300	0.8029	-0.0387	0.8029	0.8961
No log	7.0233	302	0.8978	-0.0801	0.8978	0.9475
No log	7.0698	304	0.8541	-0.1033	0.8541	0.9242
No log	7.1163	306	0.8624	0.0123	0.8624	0.9287
No log	7.1628	308	1.0838	-0.0253	1.0838	1.0410
No log	7.2093	310	0.9721	-0.0916	0.9721	0.9859
No log	7.2558	312	0.7862	0.0395	0.7862	0.8867
No log	7.3023	314	0.9474	-0.0970	0.9474	0.9734
No log	7.3488	316	0.9568	-0.0583	0.9568	0.9782
No log	7.3953	318	0.8237	-0.0633	0.8237	0.9076
No log	7.4419	320	0.7790	0.0282	0.7790	0.8826
No log	7.4884	322	0.8123	0.1097	0.8123	0.9013
No log	7.5349	324	0.7845	0.0282	0.7845	0.8857
No log	7.5814	326	0.8205	-0.0633	0.8205	0.9058
No log	7.6279	328	0.8794	-0.1709	0.8794	0.9377
No log	7.6744	330	0.8102	0.0081	0.8102	0.9001
No log	7.7209	332	0.8921	0.0409	0.8921	0.9445
No log	7.7674	334	0.9507	0.0233	0.9507	0.9750
No log	7.8140	336	0.8597	-0.0373	0.8597	0.9272
No log	7.8605	338	0.8287	0.0053	0.8287	0.9103
No log	7.9070	340	0.8534	-0.0268	0.8534	0.9238
No log	7.9535	342	0.8427	0.0586	0.8427	0.9180
No log	8.0	344	0.9768	-0.0101	0.9768	0.9883
No log	8.0465	346	0.9589	-0.0101	0.9589	0.9792
No log	8.0930	348	0.8747	0.0504	0.8747	0.9353
No log	8.1395	350	0.8306	-0.0567	0.8306	0.9113
No log	8.1860	352	0.8251	-0.1060	0.8251	0.9083
No log	8.2326	354	0.8221	0.0525	0.8221	0.9067
No log	8.2791	356	0.8474	0.0377	0.8474	0.9205
No log	8.3256	358	0.8379	0.0377	0.8379	0.9154
No log	8.3721	360	0.8294	0.1047	0.8294	0.9107
No log	8.4186	362	0.8169	-0.0567	0.8169	0.9038
No log	8.4651	364	0.8536	-0.0350	0.8536	0.9239
No log	8.5116	366	0.8935	-0.1249	0.8935	0.9452
No log	8.5581	368	0.8758	-0.1051	0.8758	0.9358
No log	8.6047	370	0.8388	-0.1054	0.8388	0.9159
No log	8.6512	372	0.8442	0.0953	0.8442	0.9188
No log	8.6977	374	0.8351	0.0442	0.8351	0.9138
No log	8.7442	376	0.7602	0.0374	0.7602	0.8719
No log	8.7907	378	0.7491	-0.1067	0.7491	0.8655
No log	8.8372	380	0.7333	-0.0551	0.7333	0.8563
No log	8.8837	382	0.7340	0.0909	0.7340	0.8567
No log	8.9302	384	0.9063	0.0409	0.9063	0.9520
No log	8.9767	386	1.1801	-0.0686	1.1801	1.0863
No log	9.0233	388	1.1183	-0.1285	1.1183	1.0575
No log	9.0698	390	0.8888	0.0409	0.8888	0.9428
No log	9.1163	392	0.7935	-0.0086	0.7935	0.8908
No log	9.1628	394	0.7892	0.0061	0.7892	0.8883
No log	9.2093	396	0.7934	0.0061	0.7934	0.8908
No log	9.2558	398	0.8052	-0.0195	0.8052	0.8973
No log	9.3023	400	0.8972	0.0909	0.8972	0.9472
No log	9.3488	402	0.8946	0.0867	0.8946	0.9458
No log	9.3953	404	0.8103	0.0159	0.8103	0.9001
No log	9.4419	406	0.7814	-0.0032	0.7814	0.8840
No log	9.4884	408	0.7815	-0.0493	0.7815	0.8840
No log	9.5349	410	0.7691	-0.0179	0.7691	0.8770
No log	9.5814	412	0.8752	0.0748	0.8752	0.9355
No log	9.6279	414	0.8985	0.0748	0.8985	0.9479
No log	9.6744	416	0.8367	0.0999	0.8367	0.9147
No log	9.7209	418	0.8241	-0.0138	0.8241	0.9078
No log	9.7674	420	0.8359	-0.0108	0.8359	0.9143
No log	9.8140	422	0.8528	0.0562	0.8528	0.9234
No log	9.8605	424	0.8956	-0.0056	0.8956	0.9464
No log	9.9070	426	0.8220	0.0628	0.8220	0.9066
No log	9.9535	428	0.7761	0.0814	0.7761	0.8810
No log	10.0	430	0.7706	0.0	0.7706	0.8778
No log	10.0465	432	0.7839	-0.0062	0.7839	0.8854
No log	10.0930	434	0.8486	0.1047	0.8486	0.9212
No log	10.1395	436	0.9188	0.0377	0.9188	0.9585
No log	10.1860	438	0.8851	0.0123	0.8851	0.9408
No log	10.2326	440	0.8578	-0.0391	0.8578	0.9262
No log	10.2791	442	0.8823	-0.0572	0.8823	0.9393
No log	10.3256	444	0.8752	-0.0522	0.8752	0.9355
No log	10.3721	446	0.8355	-0.0339	0.8355	0.9140
No log	10.4186	448	0.7935	0.0465	0.7935	0.8908
No log	10.4651	450	0.7623	0.0432	0.7623	0.8731
No log	10.5116	452	0.7688	0.0869	0.7688	0.8768
No log	10.5581	454	0.8098	0.0205	0.8098	0.8999
No log	10.6047	456	0.8259	0.0690	0.8259	0.9088
No log	10.6512	458	0.8211	0.0412	0.8211	0.9061
No log	10.6977	460	0.8330	0.0323	0.8330	0.9127
No log	10.7442	462	0.8602	-0.0132	0.8602	0.9275
No log	10.7907	464	0.8887	-0.0658	0.8887	0.9427
No log	10.8372	466	0.9309	-0.0067	0.9309	0.9648
No log	10.8837	468	1.0308	-0.0076	1.0308	1.0153
No log	10.9302	470	1.2221	-0.0942	1.2221	1.1055
No log	10.9767	472	1.1287	-0.1609	1.1287	1.0624
No log	11.0233	474	0.9295	-0.0076	0.9295	0.9641
No log	11.0698	476	0.8617	0.0488	0.8617	0.9283
No log	11.1163	478	0.8535	-0.0259	0.8535	0.9239
No log	11.1628	480	0.8320	-0.0113	0.8320	0.9121
No log	11.2093	482	0.8956	0.0287	0.8956	0.9464
No log	11.2558	484	0.9709	-0.1616	0.9709	0.9854
No log	11.3023	486	0.9413	0.0233	0.9413	0.9702
No log	11.3488	488	0.9014	-0.0232	0.9014	0.9494
No log	11.3953	490	0.8977	-0.0563	0.8977	0.9475
No log	11.4419	492	0.9004	0.0296	0.9004	0.9489
No log	11.4884	494	0.8773	0.0023	0.8773	0.9366
No log	11.5349	496	0.9656	0.0377	0.9656	0.9826
No log	11.5814	498	1.0226	0.0207	1.0226	1.0112
0.3675	11.6279	500	0.9586	0.0676	0.9586	0.9791
0.3675	11.6744	502	0.9140	0.0456	0.9140	0.9561
0.3675	11.7209	504	0.8843	0.0525	0.8843	0.9404
0.3675	11.7674	506	0.8565	0.1146	0.8565	0.9255
0.3675	11.8140	508	0.8586	0.0723	0.8586	0.9266
0.3675	11.8605	510	0.8749	0.1506	0.8749	0.9354
0.3675	11.9070	512	0.9568	-0.0909	0.9568	0.9781
0.3675	11.9535	514	0.9978	-0.1620	0.9978	0.9989
0.3675	12.0	516	0.9323	0.1150	0.9323	0.9656
0.3675	12.0465	518	0.8731	0.1395	0.8731	0.9344
0.3675	12.0930	520	0.8454	0.0269	0.8454	0.9194
0.3675	12.1395	522	0.8543	0.0709	0.8543	0.9243
0.3675	12.1860	524	0.8472	0.0327	0.8472	0.9204
0.3675	12.2326	526	0.8182	0.0327	0.8182	0.9045
0.3675	12.2791	528	0.8078	0.1627	0.8078	0.8988
0.3675	12.3256	530	0.8084	0.1627	0.8084	0.8991
0.3675	12.3721	532	0.7849	0.1199	0.7849	0.8860
0.3675	12.4186	534	0.7831	0.0821	0.7831	0.8849
0.3675	12.4651	536	0.8110	0.1627	0.8110	0.9006
0.3675	12.5116	538	0.8596	0.0999	0.8596	0.9272
0.3675	12.5581	540	0.9760	-0.0163	0.9760	0.9879
0.3675	12.6047	542	0.9883	-0.0916	0.9883	0.9941
0.3675	12.6512	544	0.9053	0.0409	0.9053	0.9515
0.3675	12.6977	546	0.8519	-0.0218	0.8519	0.9230
0.3675	12.7442	548	0.8279	-0.1208	0.8279	0.9099

Framework versions

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