ArabicNewSplits7_usingALLEssays_FineTuningAraBERT_run1_AugV5_k10_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: 0.8020
• Qwk: 0.6716
• Mse: 0.8020
• Rmse: 0.8956

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	0.0417	2	7.1475	0.0057	7.1475	2.6735
No log	0.0833	4	4.5387	0.0500	4.5387	2.1304
No log	0.125	6	3.7582	-0.0729	3.7582	1.9386
No log	0.1667	8	2.7595	0.0667	2.7595	1.6612
No log	0.2083	10	1.9346	0.0855	1.9346	1.3909
No log	0.25	12	1.8941	0.1754	1.8941	1.3763
No log	0.2917	14	2.0940	0.1311	2.0940	1.4471
No log	0.3333	16	1.9429	0.1913	1.9429	1.3939
No log	0.375	18	1.6877	0.0943	1.6877	1.2991
No log	0.4167	20	1.6567	0.1495	1.6567	1.2871
No log	0.4583	22	1.8104	0.2143	1.8104	1.3455
No log	0.5	24	1.7755	0.2632	1.7755	1.3325
No log	0.5417	26	1.9248	0.3231	1.9248	1.3874
No log	0.5833	28	2.2889	0.0828	2.2889	1.5129
No log	0.625	30	2.1792	0.1690	2.1792	1.4762
No log	0.6667	32	1.9094	0.2985	1.9094	1.3818
No log	0.7083	34	1.7320	0.3833	1.7320	1.3160
No log	0.75	36	1.7472	0.3810	1.7472	1.3218
No log	0.7917	38	1.6219	0.4065	1.6219	1.2735
No log	0.8333	40	1.6215	0.4252	1.6215	1.2734
No log	0.875	42	1.6521	0.4219	1.6521	1.2853
No log	0.9167	44	1.7211	0.3817	1.7211	1.3119
No log	0.9583	46	1.9497	0.2609	1.9497	1.3963
No log	1.0	48	2.2094	0.1733	2.2094	1.4864
No log	1.0417	50	2.3753	0.1429	2.3753	1.5412
No log	1.0833	52	2.2589	0.1733	2.2589	1.5030
No log	1.125	54	1.7853	0.3741	1.7853	1.3361
No log	1.1667	56	1.3593	0.4516	1.3593	1.1659
No log	1.2083	58	1.2124	0.4959	1.2124	1.1011
No log	1.25	60	1.1729	0.5082	1.1729	1.0830
No log	1.2917	62	1.2108	0.5041	1.2108	1.1003
No log	1.3333	64	1.3913	0.3876	1.3913	1.1796
No log	1.375	66	1.3991	0.3788	1.3991	1.1828
No log	1.4167	68	1.3059	0.5113	1.3059	1.1427
No log	1.4583	70	1.1977	0.4921	1.1977	1.0944
No log	1.5	72	1.1296	0.4706	1.1296	1.0628
No log	1.5417	74	1.1220	0.5124	1.1220	1.0593
No log	1.5833	76	1.1386	0.5	1.1386	1.0671
No log	1.625	78	1.2571	0.48	1.2571	1.1212
No log	1.6667	80	1.7051	0.3308	1.7051	1.3058
No log	1.7083	82	1.5068	0.3492	1.5068	1.2275
No log	1.75	84	1.3492	0.4463	1.3492	1.1615
No log	1.7917	86	1.4552	0.4160	1.4552	1.2063
No log	1.8333	88	1.4136	0.4320	1.4136	1.1890
No log	1.875	90	1.2731	0.4228	1.2731	1.1283
No log	1.9167	92	1.2191	0.4724	1.2191	1.1041
No log	1.9583	94	1.1858	0.4480	1.1858	1.0890
No log	2.0	96	1.0245	0.4576	1.0245	1.0122
No log	2.0417	98	1.0158	0.4538	1.0158	1.0079
No log	2.0833	100	1.0519	0.5366	1.0519	1.0256
No log	2.125	102	1.2391	0.5522	1.2391	1.1132
No log	2.1667	104	1.3330	0.5217	1.3330	1.1545
No log	2.2083	106	1.2862	0.5075	1.2862	1.1341
No log	2.25	108	1.2394	0.5	1.2394	1.1133
No log	2.2917	110	1.0682	0.4715	1.0682	1.0336
No log	2.3333	112	1.0672	0.4839	1.0672	1.0330
No log	2.375	114	1.0713	0.5238	1.0713	1.0350
No log	2.4167	116	1.0957	0.528	1.0957	1.0468
No log	2.4583	118	1.1114	0.512	1.1114	1.0542
No log	2.5	120	1.1795	0.4355	1.1795	1.0861
No log	2.5417	122	1.3321	0.4848	1.3321	1.1542
No log	2.5833	124	1.2781	0.4531	1.2781	1.1305
No log	2.625	126	1.1176	0.4724	1.1176	1.0572
No log	2.6667	128	1.0868	0.5385	1.0868	1.0425
No log	2.7083	130	1.1198	0.4961	1.1198	1.0582
No log	2.75	132	1.1447	0.5038	1.1447	1.0699
No log	2.7917	134	1.2781	0.5113	1.2781	1.1305
No log	2.8333	136	1.3161	0.4361	1.3161	1.1472
No log	2.875	138	1.4624	0.4672	1.4624	1.2093
No log	2.9167	140	1.4755	0.4823	1.4755	1.2147
No log	2.9583	142	1.2729	0.5191	1.2729	1.1282
No log	3.0	144	1.0645	0.5385	1.0645	1.0318
No log	3.0417	146	1.0647	0.5397	1.0647	1.0318
No log	3.0833	148	1.3210	0.4375	1.3210	1.1494
No log	3.125	150	1.8014	0.3134	1.8014	1.3421
No log	3.1667	152	1.7042	0.3433	1.7042	1.3055
No log	3.2083	154	1.2605	0.4252	1.2605	1.1227
No log	3.25	156	1.0463	0.5581	1.0463	1.0229
No log	3.2917	158	1.0298	0.5692	1.0298	1.0148
No log	3.3333	160	1.0421	0.5354	1.0421	1.0208
No log	3.375	162	1.1108	0.5238	1.1108	1.0539
No log	3.4167	164	1.3262	0.5152	1.3262	1.1516
No log	3.4583	166	1.5974	0.4218	1.5974	1.2639
No log	3.5	168	1.6062	0.4487	1.6062	1.2674
No log	3.5417	170	1.4840	0.4507	1.4840	1.2182
No log	3.5833	172	1.3711	0.4493	1.3711	1.1709
No log	3.625	174	1.5443	0.3623	1.5443	1.2427
No log	3.6667	176	1.6465	0.3741	1.6465	1.2832
No log	3.7083	178	1.8321	0.3165	1.8321	1.3535
No log	3.75	180	1.6930	0.3212	1.6930	1.3011
No log	3.7917	182	1.6185	0.3212	1.6185	1.2722
No log	3.8333	184	1.3379	0.4627	1.3379	1.1567
No log	3.875	186	1.1822	0.5469	1.1822	1.0873
No log	3.9167	188	1.1465	0.528	1.1465	1.0708
No log	3.9583	190	1.1991	0.4885	1.1991	1.0950
No log	4.0	192	1.4158	0.4571	1.4158	1.1899
No log	4.0417	194	1.5754	0.4658	1.5754	1.2551
No log	4.0833	196	1.7055	0.4359	1.7055	1.3059
No log	4.125	198	1.3111	0.4722	1.3111	1.1450
No log	4.1667	200	0.9901	0.5926	0.9901	0.9950
No log	4.2083	202	0.9748	0.6324	0.9748	0.9873
No log	4.25	204	1.1694	0.5038	1.1694	1.0814
No log	4.2917	206	1.1761	0.5038	1.1761	1.0845
No log	4.3333	208	0.9501	0.6519	0.9501	0.9747
No log	4.375	210	0.8746	0.6286	0.8746	0.9352
No log	4.4167	212	0.9481	0.625	0.9481	0.9737
No log	4.4583	214	0.9076	0.6331	0.9076	0.9527
No log	4.5	216	0.8859	0.6765	0.8859	0.9412
No log	4.5417	218	0.9920	0.5926	0.9920	0.9960
No log	4.5833	220	1.1178	0.5455	1.1178	1.0573
No log	4.625	222	1.2028	0.4965	1.2028	1.0967
No log	4.6667	224	1.0371	0.6286	1.0371	1.0184
No log	4.7083	226	0.9016	0.6286	0.9016	0.9495
No log	4.75	228	0.9495	0.6377	0.9495	0.9744
No log	4.7917	230	0.9904	0.6423	0.9904	0.9952
No log	4.8333	232	0.9565	0.6475	0.9565	0.9780
No log	4.875	234	0.9486	0.5354	0.9486	0.9740
No log	4.9167	236	1.0847	0.5303	1.0847	1.0415
No log	4.9583	238	1.1789	0.5522	1.1789	1.0858
No log	5.0	240	1.1450	0.5401	1.1450	1.0700
No log	5.0417	242	1.0267	0.5821	1.0267	1.0133
No log	5.0833	244	0.9350	0.5581	0.9350	0.9670
No log	5.125	246	0.9180	0.5846	0.9180	0.9581
No log	5.1667	248	0.9529	0.6119	0.9529	0.9762
No log	5.2083	250	1.0031	0.5606	1.0031	1.0015
No log	5.25	252	1.0270	0.5846	1.0270	1.0134
No log	5.2917	254	1.0205	0.5736	1.0205	1.0102
No log	5.3333	256	0.9793	0.5692	0.9793	0.9896
No log	5.375	258	1.0338	0.5669	1.0338	1.0168
No log	5.4167	260	1.0885	0.5736	1.0885	1.0433
No log	5.4583	262	1.0381	0.6324	1.0381	1.0189
No log	5.5	264	0.9983	0.5802	0.9983	0.9991
No log	5.5417	266	0.9803	0.6061	0.9803	0.9901
No log	5.5833	268	0.9669	0.6222	0.9669	0.9833
No log	5.625	270	0.9409	0.6423	0.9409	0.9700
No log	5.6667	272	0.9504	0.6143	0.9504	0.9749
No log	5.7083	274	0.9298	0.6331	0.9298	0.9642
No log	5.75	276	0.9224	0.6479	0.9224	0.9604
No log	5.7917	278	0.9210	0.6429	0.9210	0.9597
No log	5.8333	280	1.0602	0.5850	1.0602	1.0297
No log	5.875	282	1.2182	0.5333	1.2182	1.1037
No log	5.9167	284	1.2053	0.5442	1.2053	1.0979
No log	5.9583	286	1.0630	0.5672	1.0630	1.0310
No log	6.0	288	1.0003	0.5161	1.0003	1.0001
No log	6.0417	290	1.0029	0.5161	1.0029	1.0015
No log	6.0833	292	0.9824	0.512	0.9824	0.9912
No log	6.125	294	1.0289	0.5564	1.0289	1.0143
No log	6.1667	296	1.0837	0.5882	1.0837	1.0410
No log	6.2083	298	1.0317	0.5821	1.0317	1.0157
No log	6.25	300	0.9389	0.5736	0.9389	0.9690
No log	6.2917	302	0.9421	0.6471	0.9421	0.9706
No log	6.3333	304	0.9498	0.6812	0.9498	0.9746
No log	6.375	306	0.9504	0.6119	0.9504	0.9749
No log	6.4167	308	0.9431	0.6423	0.9431	0.9711
No log	6.4583	310	0.9361	0.6107	0.9361	0.9675
No log	6.5	312	0.9337	0.6000	0.9337	0.9663
No log	6.5417	314	0.9130	0.5938	0.9130	0.9555
No log	6.5833	316	0.9111	0.6154	0.9111	0.9545
No log	6.625	318	0.9506	0.5581	0.9506	0.9750
No log	6.6667	320	1.1066	0.5781	1.1066	1.0519
No log	6.7083	322	1.2252	0.4697	1.2252	1.1069
No log	6.75	324	1.1779	0.5455	1.1779	1.0853
No log	6.7917	326	1.0100	0.5846	1.0100	1.0050
No log	6.8333	328	0.9697	0.5538	0.9697	0.9847
No log	6.875	330	1.0443	0.5649	1.0443	1.0219
No log	6.9167	332	1.1239	0.5426	1.1239	1.0601
No log	6.9583	334	1.0675	0.5538	1.0675	1.0332
No log	7.0	336	0.9835	0.5692	0.9835	0.9917
No log	7.0417	338	0.9737	0.5736	0.9737	0.9868
No log	7.0833	340	0.9925	0.6165	0.9925	0.9963
No log	7.125	342	0.9899	0.5781	0.9899	0.9949
No log	7.1667	344	0.9716	0.5781	0.9716	0.9857
No log	7.2083	346	0.9403	0.5891	0.9403	0.9697
No log	7.25	348	0.9527	0.5846	0.9527	0.9761
No log	7.2917	350	0.9431	0.5538	0.9431	0.9712
No log	7.3333	352	0.8686	0.6107	0.8686	0.9320
No log	7.375	354	0.8382	0.6107	0.8382	0.9155
No log	7.4167	356	0.8053	0.6107	0.8053	0.8974
No log	7.4583	358	0.8205	0.6	0.8205	0.9058
No log	7.5	360	0.8303	0.5736	0.8303	0.9112
No log	7.5417	362	0.8673	0.5469	0.8673	0.9313
No log	7.5833	364	0.8757	0.5469	0.8757	0.9358
No log	7.625	366	0.8919	0.5397	0.8919	0.9444
No log	7.6667	368	0.8479	0.5781	0.8479	0.9208
No log	7.7083	370	0.8046	0.6515	0.8046	0.8970
No log	7.75	372	0.7988	0.6316	0.7988	0.8937
No log	7.7917	374	0.7906	0.6667	0.7906	0.8892
No log	7.8333	376	0.7650	0.7143	0.7650	0.8746
No log	7.875	378	0.7527	0.7260	0.7527	0.8676
No log	7.9167	380	0.7593	0.7397	0.7593	0.8714
No log	7.9583	382	0.7937	0.7042	0.7937	0.8909
No log	8.0	384	0.8249	0.6906	0.8249	0.9082
No log	8.0417	386	0.8179	0.7059	0.8179	0.9044
No log	8.0833	388	0.8194	0.6715	0.8194	0.9052
No log	8.125	390	0.8248	0.6667	0.8248	0.9082
No log	8.1667	392	0.8125	0.7153	0.8125	0.9014
No log	8.2083	394	0.7892	0.7153	0.7892	0.8884
No log	8.25	396	0.7856	0.6957	0.7856	0.8864
No log	8.2917	398	0.7902	0.6957	0.7902	0.8890
No log	8.3333	400	0.8042	0.6765	0.8042	0.8968
No log	8.375	402	0.7897	0.7007	0.7897	0.8886
No log	8.4167	404	0.8011	0.6912	0.8011	0.8951
No log	8.4583	406	0.8475	0.6165	0.8475	0.9206
No log	8.5	408	0.9175	0.6269	0.9175	0.9579
No log	8.5417	410	0.9465	0.6107	0.9465	0.9729
No log	8.5833	412	0.9042	0.6	0.9042	0.9509
No log	8.625	414	0.9159	0.6212	0.9159	0.9570
No log	8.6667	416	0.9994	0.5882	0.9994	0.9997
No log	8.7083	418	1.0306	0.5797	1.0306	1.0152
No log	8.75	420	0.9958	0.5899	0.9958	0.9979
No log	8.7917	422	0.8805	0.6131	0.8805	0.9384
No log	8.8333	424	0.7864	0.6567	0.7864	0.8868
No log	8.875	426	0.7636	0.7101	0.7636	0.8738
No log	8.9167	428	0.8121	0.6567	0.8121	0.9012
No log	8.9583	430	0.9851	0.6131	0.9851	0.9925
No log	9.0	432	1.2736	0.6282	1.2736	1.1285
No log	9.0417	434	1.3338	0.5385	1.3338	1.1549
No log	9.0833	436	1.1024	0.5714	1.1024	1.0500
No log	9.125	438	0.9021	0.6316	0.9021	0.9498
No log	9.1667	440	0.8778	0.6	0.8778	0.9369
No log	9.2083	442	0.8606	0.6767	0.8606	0.9277
No log	9.25	444	0.8119	0.6815	0.8119	0.9010
No log	9.2917	446	0.7896	0.6912	0.7896	0.8886
No log	9.3333	448	0.7783	0.6912	0.7783	0.8822
No log	9.375	450	0.7588	0.6716	0.7588	0.8711
No log	9.4167	452	0.7508	0.6716	0.7508	0.8665
No log	9.4583	454	0.7617	0.6617	0.7617	0.8727
No log	9.5	456	0.8128	0.6765	0.8128	0.9015
No log	9.5417	458	0.8206	0.6667	0.8206	0.9059
No log	9.5833	460	0.9060	0.6165	0.9060	0.9518
No log	9.625	462	0.9583	0.6525	0.9583	0.9789
No log	9.6667	464	0.8824	0.6475	0.8824	0.9394
No log	9.7083	466	0.7621	0.6866	0.7621	0.8730
No log	9.75	468	0.7432	0.6567	0.7432	0.8621
No log	9.7917	470	0.7623	0.6567	0.7623	0.8731
No log	9.8333	472	0.8109	0.6269	0.8109	0.9005
No log	9.875	474	0.8838	0.6715	0.8838	0.9401
No log	9.9167	476	1.0444	0.5942	1.0444	1.0219
No log	9.9583	478	1.2162	0.5634	1.2162	1.1028
No log	10.0	480	1.3808	0.4865	1.3808	1.1751
No log	10.0417	482	1.2546	0.5442	1.2546	1.1201
No log	10.0833	484	0.9457	0.6286	0.9457	0.9725
No log	10.125	486	0.8187	0.6364	0.8187	0.9048
No log	10.1667	488	0.8197	0.6866	0.8197	0.9054
No log	10.2083	490	0.8250	0.6815	0.8250	0.9083
No log	10.25	492	0.8818	0.6618	0.8818	0.9391
No log	10.2917	494	0.9350	0.5649	0.9350	0.9670
No log	10.3333	496	0.9033	0.6569	0.9033	0.9504
No log	10.375	498	0.8597	0.6667	0.8597	0.9272
0.4275	10.4167	500	0.8182	0.7007	0.8182	0.9045
0.4275	10.4583	502	0.7990	0.7007	0.7990	0.8939
0.4275	10.5	504	0.7903	0.7153	0.7903	0.8890
0.4275	10.5417	506	0.7894	0.6667	0.7894	0.8885
0.4275	10.5833	508	0.8128	0.6519	0.8128	0.9016
0.4275	10.625	510	0.8696	0.6197	0.8696	0.9325
0.4275	10.6667	512	0.8596	0.6074	0.8596	0.9271
0.4275	10.7083	514	0.8020	0.6716	0.8020	0.8956

Framework versions

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