ArabicNewSplits7_FineTuningAraBERT_run2_AugV5_k10_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: 0.8461
• Qwk: 0.1362
• Mse: 0.8461
• Rmse: 0.9198

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	0.0714	2	3.7931	-0.0163	3.7931	1.9476
No log	0.1429	4	1.7473	0.0943	1.7473	1.3218
No log	0.2143	6	1.2333	0.1067	1.2333	1.1105
No log	0.2857	8	1.2190	0.0586	1.2190	1.1041
No log	0.3571	10	1.1768	0.0586	1.1768	1.0848
No log	0.4286	12	1.1086	-0.0164	1.1086	1.0529
No log	0.5	14	1.0054	-0.0398	1.0054	1.0027
No log	0.5714	16	0.9601	-0.0638	0.9601	0.9799
No log	0.6429	18	1.0323	-0.1290	1.0323	1.0160
No log	0.7143	20	1.0820	-0.1575	1.0820	1.0402
No log	0.7857	22	1.0320	-0.1278	1.0320	1.0159
No log	0.8571	24	1.0577	-0.1920	1.0577	1.0285
No log	0.9286	26	1.0587	-0.1602	1.0587	1.0289
No log	1.0	28	1.1240	-0.0977	1.1240	1.0602
No log	1.0714	30	1.2121	-0.0987	1.2121	1.1010
No log	1.1429	32	1.2955	-0.0704	1.2955	1.1382
No log	1.2143	34	1.1399	-0.0982	1.1399	1.0677
No log	1.2857	36	1.2880	-0.0423	1.2880	1.1349
No log	1.3571	38	1.6238	0.0	1.6238	1.2743
No log	1.4286	40	1.4649	0.0	1.4649	1.2103
No log	1.5	42	1.3170	0.0	1.3170	1.1476
No log	1.5714	44	1.0074	-0.0728	1.0074	1.0037
No log	1.6429	46	0.7913	-0.0725	0.7913	0.8895
No log	1.7143	48	0.7299	-0.0069	0.7299	0.8543
No log	1.7857	50	0.7275	-0.0035	0.7275	0.8530
No log	1.8571	52	0.8108	0.1148	0.8108	0.9005
No log	1.9286	54	1.0706	-0.0207	1.0706	1.0347
No log	2.0	56	1.5628	0.0	1.5628	1.2501
No log	2.0714	58	1.7116	-0.0015	1.7116	1.3083
No log	2.1429	60	1.4090	-0.0207	1.4090	1.1870
No log	2.2143	62	0.9666	-0.1274	0.9666	0.9832
No log	2.2857	64	0.7896	-0.0725	0.7896	0.8886
No log	2.3571	66	0.7379	-0.0188	0.7379	0.8590
No log	2.4286	68	0.7253	0.0479	0.7253	0.8517
No log	2.5	70	0.7317	-0.0188	0.7317	0.8554
No log	2.5714	72	0.7414	-0.0188	0.7414	0.8611
No log	2.6429	74	0.7692	-0.0264	0.7692	0.8770
No log	2.7143	76	0.8360	-0.1676	0.8360	0.9143
No log	2.7857	78	1.2867	0.0379	1.2867	1.1343
No log	2.8571	80	1.5995	0.0	1.5995	1.2647
No log	2.9286	82	1.5630	0.0	1.5630	1.2502
No log	3.0	84	1.4121	0.0016	1.4121	1.1883
No log	3.0714	86	0.9479	0.0378	0.9479	0.9736
No log	3.1429	88	0.8090	-0.0215	0.8090	0.8994
No log	3.2143	90	1.2409	-0.0229	1.2409	1.1140
No log	3.2857	92	0.9916	-0.0490	0.9916	0.9958
No log	3.3571	94	0.7256	0.0416	0.7256	0.8518
No log	3.4286	96	0.9127	0.0848	0.9127	0.9554
No log	3.5	98	1.2301	0.0279	1.2301	1.1091
No log	3.5714	100	1.2975	-0.0247	1.2975	1.1391
No log	3.6429	102	0.9897	-0.0638	0.9897	0.9948
No log	3.7143	104	0.7811	0.0296	0.7811	0.8838
No log	3.7857	106	0.7629	0.1498	0.7629	0.8734
No log	3.8571	108	0.7401	0.0334	0.7401	0.8603
No log	3.9286	110	0.7284	0.0334	0.7284	0.8535
No log	4.0	112	0.7358	0.0807	0.7358	0.8578
No log	4.0714	114	0.7242	0.0374	0.7242	0.8510
No log	4.1429	116	0.7582	0.0973	0.7582	0.8707
No log	4.2143	118	0.7734	0.0759	0.7734	0.8794
No log	4.2857	120	0.7728	0.0714	0.7728	0.8791
No log	4.3571	122	0.7595	0.1292	0.7595	0.8715
No log	4.4286	124	0.7760	0.1463	0.7760	0.8809
No log	4.5	126	0.7632	0.1249	0.7632	0.8736
No log	4.5714	128	1.1024	0.0147	1.1024	1.0499
No log	4.6429	130	1.3365	0.1042	1.3365	1.1561
No log	4.7143	132	0.8847	-0.0240	0.8847	0.9406
No log	4.7857	134	0.9086	0.1277	0.9086	0.9532
No log	4.8571	136	1.0115	-0.0197	1.0115	1.0057
No log	4.9286	138	1.1096	0.0691	1.1096	1.0534
No log	5.0	140	1.0296	0.0871	1.0296	1.0147
No log	5.0714	142	1.0426	0.0955	1.0426	1.0211
No log	5.1429	144	0.9628	0.0735	0.9628	0.9812
No log	5.2143	146	1.2589	0.1057	1.2589	1.1220
No log	5.2857	148	1.2144	0.0666	1.2144	1.1020
No log	5.3571	150	0.9212	0.1014	0.9212	0.9598
No log	5.4286	152	0.9146	0.1309	0.9146	0.9563
No log	5.5	154	0.8539	0.1660	0.8539	0.9241
No log	5.5714	156	0.9793	-0.0486	0.9793	0.9896
No log	5.6429	158	1.6529	0.0877	1.6529	1.2856
No log	5.7143	160	2.0591	0.0074	2.0591	1.4350
No log	5.7857	162	1.8463	0.0610	1.8463	1.3588
No log	5.8571	164	1.2087	-0.0316	1.2087	1.0994
No log	5.9286	166	0.7202	0.1691	0.7202	0.8486
No log	6.0	168	0.6593	0.0857	0.6593	0.8120
No log	6.0714	170	0.6613	0.0909	0.6613	0.8132
No log	6.1429	172	0.6729	0.1318	0.6729	0.8203
No log	6.2143	174	0.8472	0.0748	0.8472	0.9205
No log	6.2857	176	0.8771	0.0596	0.8771	0.9365
No log	6.3571	178	0.7481	0.1553	0.7481	0.8649
No log	6.4286	180	0.7192	0.2194	0.7192	0.8481
No log	6.5	182	0.7241	0.1372	0.7241	0.8509
No log	6.5714	184	0.7153	0.1815	0.7153	0.8457
No log	6.6429	186	0.7578	0.2009	0.7578	0.8705
No log	6.7143	188	0.7496	0.2009	0.7496	0.8658
No log	6.7857	190	0.7724	0.1336	0.7724	0.8789
No log	6.8571	192	0.7451	0.0670	0.7451	0.8632
No log	6.9286	194	0.7786	0.0588	0.7786	0.8824
No log	7.0	196	0.7940	0.0071	0.7940	0.8911
No log	7.0714	198	0.7683	0.0454	0.7683	0.8765
No log	7.1429	200	0.7944	0.0518	0.7944	0.8913
No log	7.2143	202	0.8532	0.0476	0.8532	0.9237
No log	7.2857	204	1.1917	0.0578	1.1917	1.0917
No log	7.3571	206	1.0384	-0.0571	1.0384	1.0190
No log	7.4286	208	0.7417	0.2053	0.7417	0.8612
No log	7.5	210	0.8007	0.1419	0.8007	0.8948
No log	7.5714	212	0.8175	0.1412	0.8175	0.9042
No log	7.6429	214	0.7638	0.2153	0.7638	0.8740
No log	7.7143	216	0.8834	-0.0008	0.8834	0.9399
No log	7.7857	218	0.8507	0.1365	0.8507	0.9223
No log	7.8571	220	0.8029	0.2118	0.8029	0.8961
No log	7.9286	222	0.8127	0.2132	0.8127	0.9015
No log	8.0	224	0.7567	0.0869	0.7567	0.8699
No log	8.0714	226	0.7917	0.0714	0.7917	0.8898
No log	8.1429	228	0.8053	0.1146	0.8053	0.8974
No log	8.2143	230	0.8519	0.1324	0.8519	0.9230
No log	8.2857	232	0.8206	0.1796	0.8206	0.9059
No log	8.3571	234	0.8791	0.2430	0.8791	0.9376
No log	8.4286	236	0.8956	0.0936	0.8956	0.9464
No log	8.5	238	0.8423	0.1367	0.8423	0.9178
No log	8.5714	240	0.7330	0.0436	0.7330	0.8561
No log	8.6429	242	0.6988	0.1379	0.6988	0.8360
No log	8.7143	244	0.8530	0.0525	0.8530	0.9236
No log	8.7857	246	0.8828	0.0068	0.8828	0.9396
No log	8.8571	248	0.7583	0.1379	0.7583	0.8708
No log	8.9286	250	0.7225	0.1379	0.7225	0.8500
No log	9.0	252	0.7946	0.0905	0.7946	0.8914
No log	9.0714	254	0.8124	0.0846	0.8124	0.9013
No log	9.1429	256	0.8740	0.0588	0.8740	0.9349
No log	9.2143	258	1.1843	0.0824	1.1843	1.0882
No log	9.2857	260	1.1990	0.0078	1.1990	1.0950
No log	9.3571	262	0.9186	-0.1255	0.9186	0.9584
No log	9.4286	264	0.7515	0.0828	0.7515	0.8669
No log	9.5	266	0.7597	0.1387	0.7597	0.8716
No log	9.5714	268	0.7482	0.0874	0.7482	0.8650
No log	9.6429	270	0.8206	0.1097	0.8206	0.9059
No log	9.7143	272	1.0498	0.0159	1.0498	1.0246
No log	9.7857	274	1.0279	0.0856	1.0279	1.0139
No log	9.8571	276	0.8519	0.0295	0.8519	0.9230
No log	9.9286	278	0.8671	0.1285	0.8671	0.9312
No log	10.0	280	0.8576	0.1711	0.8576	0.9261
No log	10.0714	282	0.7605	0.1347	0.7605	0.8721
No log	10.1429	284	0.7810	0.0318	0.7810	0.8838
No log	10.2143	286	0.8821	0.1105	0.8821	0.9392
No log	10.2857	288	0.8523	0.1379	0.8523	0.9232
No log	10.3571	290	0.7724	0.0863	0.7724	0.8789
No log	10.4286	292	0.7852	0.0776	0.7852	0.8861
No log	10.5	294	0.8407	0.1324	0.8407	0.9169
No log	10.5714	296	0.8925	0.1422	0.8925	0.9447
No log	10.6429	298	0.8725	0.1253	0.8725	0.9341
No log	10.7143	300	0.8569	0.2063	0.8569	0.9257
No log	10.7857	302	0.8239	0.1287	0.8239	0.9077
No log	10.8571	304	0.8500	0.0959	0.8500	0.9220
No log	10.9286	306	0.9011	-0.0490	0.9011	0.9493
No log	11.0	308	0.8347	0.1836	0.8347	0.9136
No log	11.0714	310	0.7880	0.1691	0.7880	0.8877
No log	11.1429	312	0.8176	0.2034	0.8176	0.9042
No log	11.2143	314	0.8947	-0.0031	0.8947	0.9459
No log	11.2857	316	0.8196	0.1599	0.8196	0.9053
No log	11.3571	318	0.7977	0.1769	0.7977	0.8931
No log	11.4286	320	0.8297	0.1249	0.8297	0.9109
No log	11.5	322	0.8958	0.0407	0.8958	0.9464
No log	11.5714	324	0.8983	0.0016	0.8983	0.9478
No log	11.6429	326	0.8002	0.0869	0.8002	0.8945
No log	11.7143	328	0.8199	0.2142	0.8199	0.9055
No log	11.7857	330	0.8485	0.2073	0.8485	0.9211
No log	11.8571	332	0.8476	0.1761	0.8476	0.9206
No log	11.9286	334	0.9139	-0.1088	0.9139	0.9560
No log	12.0	336	1.0293	0.0888	1.0293	1.0145
No log	12.0714	338	0.9593	0.0406	0.9593	0.9795
No log	12.1429	340	0.8874	0.1687	0.8874	0.9420
No log	12.2143	342	0.8352	0.1761	0.8352	0.9139
No log	12.2857	344	0.7984	0.0884	0.7984	0.8935
No log	12.3571	346	0.8121	0.0260	0.8121	0.9012
No log	12.4286	348	0.8166	0.0225	0.8166	0.9037
No log	12.5	350	0.7923	0.0296	0.7923	0.8901
No log	12.5714	352	0.7943	0.1835	0.7943	0.8912
No log	12.6429	354	0.8138	0.1769	0.8138	0.9021
No log	12.7143	356	0.9420	-0.0030	0.9420	0.9706
No log	12.7857	358	0.9872	-0.0052	0.9872	0.9936
No log	12.8571	360	0.8874	0.0175	0.8874	0.9420
No log	12.9286	362	0.8120	0.0303	0.8120	0.9011
No log	13.0	364	0.7774	0.1304	0.7774	0.8817
No log	13.0714	366	0.7793	0.0260	0.7793	0.8828
No log	13.1429	368	0.7971	0.0296	0.7971	0.8928
No log	13.2143	370	0.8472	0.0303	0.8472	0.9204
No log	13.2857	372	0.8887	0.0303	0.8887	0.9427
No log	13.3571	374	0.9323	0.0205	0.9323	0.9656
No log	13.4286	376	1.0037	0.0084	1.0037	1.0018
No log	13.5	378	0.9791	0.1094	0.9791	0.9895
No log	13.5714	380	0.9785	-0.0512	0.9785	0.9892
No log	13.6429	382	0.9686	-0.0032	0.9686	0.9841
No log	13.7143	384	0.8987	0.1310	0.8987	0.9480
No log	13.7857	386	0.9012	0.0709	0.9012	0.9493
No log	13.8571	388	0.9505	-0.0341	0.9505	0.9749
No log	13.9286	390	0.9536	-0.0341	0.9536	0.9765
No log	14.0	392	0.8708	0.0323	0.8708	0.9332
No log	14.0714	394	0.8793	-0.0806	0.8793	0.9377
No log	14.1429	396	0.8696	-0.0054	0.8696	0.9325
No log	14.2143	398	0.8646	-0.0766	0.8646	0.9298
No log	14.2857	400	0.8804	-0.0778	0.8804	0.9383
No log	14.3571	402	0.9399	-0.0336	0.9399	0.9695
No log	14.4286	404	0.9066	-0.0316	0.9066	0.9522
No log	14.5	406	0.8456	0.0357	0.8456	0.9196
No log	14.5714	408	0.8692	0.0834	0.8692	0.9323
No log	14.6429	410	0.8838	0.0236	0.8838	0.9401
No log	14.7143	412	0.8637	0.0791	0.8637	0.9293
No log	14.7857	414	0.8389	0.1815	0.8389	0.9159
No log	14.8571	416	0.8300	0.1815	0.8300	0.9110
No log	14.9286	418	0.8346	0.1856	0.8346	0.9136
No log	15.0	420	0.8985	-0.0767	0.8985	0.9479
No log	15.0714	422	0.8718	-0.0766	0.8718	0.9337
No log	15.1429	424	0.8373	0.1815	0.8373	0.9150
No log	15.2143	426	0.8346	0.0884	0.8346	0.9135
No log	15.2857	428	0.8436	0.0776	0.8436	0.9185
No log	15.3571	430	0.9418	-0.0425	0.9418	0.9705
No log	15.4286	432	1.0076	-0.0073	1.0076	1.0038
No log	15.5	434	0.9576	-0.0359	0.9576	0.9786
No log	15.5714	436	0.9471	0.0822	0.9471	0.9732
No log	15.6429	438	0.9630	0.0110	0.9630	0.9813
No log	15.7143	440	0.9874	0.1829	0.9874	0.9937
No log	15.7857	442	1.0033	0.0452	1.0033	1.0016
No log	15.8571	444	0.9532	0.0091	0.9532	0.9763
No log	15.9286	446	0.9238	-0.0767	0.9238	0.9611
No log	16.0	448	0.8945	-0.0755	0.8945	0.9458
No log	16.0714	450	0.8467	0.0247	0.8467	0.9202
No log	16.1429	452	0.8840	-0.0743	0.8840	0.9402
No log	16.2143	454	0.9460	-0.0755	0.9460	0.9726
No log	16.2857	456	0.9678	0.0378	0.9678	0.9838
No log	16.3571	458	0.9606	0.0361	0.9606	0.9801
No log	16.4286	460	0.9903	0.0875	0.9903	0.9952
No log	16.5	462	1.0051	0.1575	1.0051	1.0026
No log	16.5714	464	1.0356	0.0932	1.0356	1.0177
No log	16.6429	466	1.0027	0.0960	1.0027	1.0014
No log	16.7143	468	0.9286	0.0810	0.9286	0.9637
No log	16.7857	470	0.8710	0.0562	0.8710	0.9333
No log	16.8571	472	0.8872	-0.0441	0.8872	0.9419
No log	16.9286	474	0.8730	-0.0441	0.8730	0.9343
No log	17.0	476	0.8498	-0.0425	0.8498	0.9219
No log	17.0714	478	0.8643	-0.0441	0.8643	0.9297
No log	17.1429	480	0.8460	-0.0008	0.8460	0.9198
No log	17.2143	482	0.8079	0.0588	0.8079	0.8988
No log	17.2857	484	0.7694	0.1318	0.7694	0.8771
No log	17.3571	486	0.7761	0.1379	0.7761	0.8810
No log	17.4286	488	0.8171	0.0191	0.8171	0.9040
No log	17.5	490	0.8543	-0.0316	0.8543	0.9243
No log	17.5714	492	0.8294	0.1379	0.8294	0.9107
No log	17.6429	494	0.8203	0.1778	0.8203	0.9057
No log	17.7143	496	0.8388	0.1729	0.8388	0.9159
No log	17.7857	498	0.8601	0.1729	0.8601	0.9274
0.3787	17.8571	500	0.8526	0.1778	0.8526	0.9234
0.3787	17.9286	502	0.8511	0.0863	0.8511	0.9226
0.3787	18.0	504	0.8200	0.0863	0.8200	0.9056
0.3787	18.0714	506	0.7995	0.0375	0.7995	0.8942
0.3787	18.1429	508	0.8231	0.1333	0.8231	0.9072
0.3787	18.2143	510	0.8461	0.1362	0.8461	0.9198

Framework versions

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