ArabicNewSplits6_WithDuplicationsForScore5_FineTuningAraBERT_run3_AugV5_k9_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: 1.0323
• Qwk: 0.6166
• Mse: 1.0323
• Rmse: 1.0160

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	0.0556	2	2.3070	0.0083	2.3070	1.5189
No log	0.1111	4	1.5112	0.2089	1.5112	1.2293
No log	0.1667	6	1.4887	0.1209	1.4887	1.2201
No log	0.2222	8	1.5860	0.3404	1.5860	1.2594
No log	0.2778	10	1.3615	0.3094	1.3615	1.1668
No log	0.3333	12	1.2634	0.1615	1.2634	1.1240
No log	0.3889	14	1.3249	0.2943	1.3249	1.1511
No log	0.4444	16	1.4668	0.3456	1.4668	1.2111
No log	0.5	18	1.5565	0.3760	1.5565	1.2476
No log	0.5556	20	1.4928	0.3757	1.4928	1.2218
No log	0.6111	22	1.3371	0.3788	1.3371	1.1563
No log	0.6667	24	1.2722	0.3949	1.2722	1.1279
No log	0.7222	26	1.2497	0.4073	1.2497	1.1179
No log	0.7778	28	1.1069	0.4358	1.1069	1.0521
No log	0.8333	30	0.9938	0.4658	0.9938	0.9969
No log	0.8889	32	1.0428	0.3846	1.0428	1.0212
No log	0.9444	34	1.0891	0.3821	1.0891	1.0436
No log	1.0	36	0.9606	0.4483	0.9606	0.9801
No log	1.0556	38	0.8662	0.5091	0.8662	0.9307
No log	1.1111	40	1.0511	0.5890	1.0511	1.0252
No log	1.1667	42	1.4199	0.5306	1.4199	1.1916
No log	1.2222	44	1.0856	0.5447	1.0856	1.0419
No log	1.2778	46	0.8690	0.5353	0.8690	0.9322
No log	1.3333	48	1.0371	0.4382	1.0371	1.0184
No log	1.3889	50	1.0353	0.4576	1.0353	1.0175
No log	1.4444	52	0.9438	0.4550	0.9438	0.9715
No log	1.5	54	1.0470	0.5042	1.0470	1.0232
No log	1.5556	56	1.2077	0.4768	1.2077	1.0990
No log	1.6111	58	1.2334	0.5119	1.2334	1.1106
No log	1.6667	60	1.0459	0.5364	1.0459	1.0227
No log	1.7222	62	0.9095	0.5453	0.9095	0.9537
No log	1.7778	64	0.8772	0.5881	0.8772	0.9366
No log	1.8333	66	0.8631	0.6469	0.8631	0.9290
No log	1.8889	68	0.8340	0.6819	0.8340	0.9132
No log	1.9444	70	0.7701	0.6839	0.7701	0.8775
No log	2.0	72	0.7640	0.6828	0.7640	0.8741
No log	2.0556	74	0.8752	0.6777	0.8752	0.9355
No log	2.1111	76	0.8614	0.6262	0.8614	0.9281
No log	2.1667	78	0.7506	0.6342	0.7506	0.8664
No log	2.2222	80	0.7480	0.6173	0.7480	0.8649
No log	2.2778	82	0.8108	0.6466	0.8108	0.9005
No log	2.3333	84	1.0756	0.5994	1.0756	1.0371
No log	2.3889	86	1.2464	0.5950	1.2464	1.1164
No log	2.4444	88	1.0029	0.6347	1.0029	1.0014
No log	2.5	90	0.7207	0.7062	0.7207	0.8489
No log	2.5556	92	0.6840	0.6765	0.6840	0.8270
No log	2.6111	94	0.6862	0.6919	0.6862	0.8284
No log	2.6667	96	0.7443	0.7090	0.7443	0.8627
No log	2.7222	98	0.9862	0.6679	0.9862	0.9931
No log	2.7778	100	1.2122	0.6061	1.2122	1.1010
No log	2.8333	102	1.3752	0.5764	1.3752	1.1727
No log	2.8889	104	1.1925	0.5591	1.1925	1.0920
No log	2.9444	106	0.9029	0.6330	0.9029	0.9502
No log	3.0	108	0.8600	0.6309	0.8600	0.9273
No log	3.0556	110	0.9596	0.6235	0.9596	0.9796
No log	3.1111	112	1.2862	0.5130	1.2862	1.1341
No log	3.1667	114	1.4979	0.4970	1.4979	1.2239
No log	3.2222	116	1.3211	0.5322	1.3211	1.1494
No log	3.2778	118	0.9812	0.6393	0.9812	0.9906
No log	3.3333	120	0.7413	0.6801	0.7413	0.8610
No log	3.3889	122	0.7362	0.6297	0.7362	0.8580
No log	3.4444	124	0.7334	0.6374	0.7334	0.8564
No log	3.5	126	0.7489	0.7141	0.7489	0.8654
No log	3.5556	128	0.9106	0.6654	0.9106	0.9542
No log	3.6111	130	0.9548	0.6548	0.9548	0.9771
No log	3.6667	132	1.0133	0.6411	1.0133	1.0067
No log	3.7222	134	0.8566	0.7246	0.8566	0.9255
No log	3.7778	136	0.7838	0.7197	0.7838	0.8853
No log	3.8333	138	0.7886	0.7170	0.7886	0.8880
No log	3.8889	140	0.8410	0.7216	0.8410	0.9170
No log	3.9444	142	0.8889	0.7132	0.8889	0.9428
No log	4.0	144	0.8719	0.7086	0.8719	0.9337
No log	4.0556	146	1.0083	0.6520	1.0083	1.0041
No log	4.1111	148	1.1492	0.5717	1.1492	1.0720
No log	4.1667	150	1.1634	0.5774	1.1634	1.0786
No log	4.2222	152	1.1890	0.5746	1.1890	1.0904
No log	4.2778	154	1.2794	0.5587	1.2794	1.1311
No log	4.3333	156	1.0952	0.6002	1.0952	1.0465
No log	4.3889	158	0.8717	0.6812	0.8717	0.9336
No log	4.4444	160	0.8460	0.6796	0.8460	0.9198
No log	4.5	162	0.9269	0.6719	0.9269	0.9627
No log	4.5556	164	1.1100	0.5948	1.1100	1.0536
No log	4.6111	166	1.3890	0.5493	1.3890	1.1785
No log	4.6667	168	1.5014	0.5450	1.5014	1.2253
No log	4.7222	170	1.3516	0.5727	1.3516	1.1626
No log	4.7778	172	1.1684	0.6019	1.1684	1.0809
No log	4.8333	174	0.9841	0.6154	0.9841	0.9920
No log	4.8889	176	0.9613	0.6241	0.9613	0.9805
No log	4.9444	178	1.0630	0.5974	1.0630	1.0310
No log	5.0	180	1.1481	0.5849	1.1481	1.0715
No log	5.0556	182	1.0572	0.5535	1.0572	1.0282
No log	5.1111	184	0.9898	0.5790	0.9898	0.9949
No log	5.1667	186	0.8986	0.6469	0.8986	0.9479
No log	5.2222	188	0.9594	0.6008	0.9594	0.9795
No log	5.2778	190	0.9882	0.5891	0.9882	0.9941
No log	5.3333	192	1.1413	0.5797	1.1413	1.0683
No log	5.3889	194	1.4183	0.5382	1.4183	1.1909
No log	5.4444	196	1.5295	0.5434	1.5295	1.2367
No log	5.5	198	1.3856	0.5700	1.3856	1.1771
No log	5.5556	200	1.1395	0.5725	1.1395	1.0675
No log	5.6111	202	0.9377	0.6420	0.9377	0.9684
No log	5.6667	204	0.8458	0.6659	0.8458	0.9197
No log	5.7222	206	0.8441	0.6659	0.8441	0.9188
No log	5.7778	208	0.9339	0.6254	0.9339	0.9664
No log	5.8333	210	1.1841	0.5848	1.1841	1.0882
No log	5.8889	212	1.3891	0.5472	1.3891	1.1786
No log	5.9444	214	1.4557	0.5603	1.4557	1.2065
No log	6.0	216	1.3810	0.5500	1.3810	1.1751
No log	6.0556	218	1.2005	0.5852	1.2005	1.0957
No log	6.1111	220	1.0625	0.5880	1.0625	1.0308
No log	6.1667	222	1.0305	0.5989	1.0305	1.0151
No log	6.2222	224	1.0418	0.5788	1.0418	1.0207
No log	6.2778	226	1.0886	0.5564	1.0886	1.0433
No log	6.3333	228	1.1663	0.5645	1.1663	1.0799
No log	6.3889	230	1.1017	0.5611	1.1017	1.0496
No log	6.4444	232	1.0004	0.6298	1.0004	1.0002
No log	6.5	234	0.9501	0.6704	0.9501	0.9747
No log	6.5556	236	1.0040	0.6194	1.0040	1.0020
No log	6.6111	238	1.1461	0.5639	1.1461	1.0705
No log	6.6667	240	1.2075	0.5621	1.2075	1.0988
No log	6.7222	242	1.1184	0.5812	1.1184	1.0576
No log	6.7778	244	0.9562	0.6543	0.9562	0.9779
No log	6.8333	246	0.8453	0.6982	0.8453	0.9194
No log	6.8889	248	0.8411	0.6958	0.8411	0.9171
No log	6.9444	250	0.8906	0.6873	0.8906	0.9437
No log	7.0	252	0.9838	0.6393	0.9838	0.9919
No log	7.0556	254	1.0168	0.5821	1.0168	1.0083
No log	7.1111	256	1.0269	0.5746	1.0269	1.0134
No log	7.1667	258	1.0414	0.5734	1.0414	1.0205
No log	7.2222	260	1.0379	0.5853	1.0379	1.0188
No log	7.2778	262	1.0574	0.5947	1.0574	1.0283
No log	7.3333	264	0.9861	0.6318	0.9861	0.9930
No log	7.3889	266	0.8988	0.7064	0.8988	0.9481
No log	7.4444	268	0.8753	0.7064	0.8753	0.9356
No log	7.5	270	0.9267	0.6816	0.9267	0.9626
No log	7.5556	272	1.0087	0.6168	1.0087	1.0044
No log	7.6111	274	1.0414	0.5875	1.0414	1.0205
No log	7.6667	276	1.0443	0.5831	1.0443	1.0219
No log	7.7222	278	1.0492	0.5679	1.0492	1.0243
No log	7.7778	280	0.9855	0.5986	0.9855	0.9927
No log	7.8333	282	0.9296	0.6573	0.9296	0.9642
No log	7.8889	284	0.8903	0.6739	0.8903	0.9435
No log	7.9444	286	0.8858	0.6739	0.8858	0.9411
No log	8.0	288	0.9264	0.6687	0.9264	0.9625
No log	8.0556	290	0.9650	0.6720	0.9650	0.9823
No log	8.1111	292	1.0537	0.6195	1.0537	1.0265
No log	8.1667	294	1.1123	0.6141	1.1123	1.0547
No log	8.2222	296	1.0882	0.6232	1.0882	1.0432
No log	8.2778	298	1.0478	0.6205	1.0478	1.0236
No log	8.3333	300	0.9939	0.6431	0.9939	0.9970
No log	8.3889	302	0.9287	0.6958	0.9287	0.9637
No log	8.4444	304	0.8791	0.7101	0.8791	0.9376
No log	8.5	306	0.8644	0.7096	0.8644	0.9297
No log	8.5556	308	0.8871	0.7176	0.8871	0.9419
No log	8.6111	310	0.9381	0.7053	0.9381	0.9686
No log	8.6667	312	1.0135	0.6279	1.0135	1.0067
No log	8.7222	314	1.0544	0.6145	1.0544	1.0269
No log	8.7778	316	1.0684	0.6204	1.0684	1.0336
No log	8.8333	318	1.0842	0.6120	1.0842	1.0413
No log	8.8889	320	1.0748	0.6204	1.0748	1.0367
No log	8.9444	322	1.0401	0.6145	1.0401	1.0199
No log	9.0	324	0.9968	0.6209	0.9968	0.9984
No log	9.0556	326	0.9781	0.6530	0.9781	0.9890
No log	9.1111	328	0.9607	0.6713	0.9607	0.9802
No log	9.1667	330	0.9690	0.6595	0.9690	0.9844
No log	9.2222	332	0.9846	0.6414	0.9846	0.9923
No log	9.2778	334	1.0147	0.6085	1.0147	1.0073
No log	9.3333	336	1.0564	0.6092	1.0564	1.0278
No log	9.3889	338	1.0855	0.6040	1.0855	1.0419
No log	9.4444	340	1.1063	0.5858	1.1063	1.0518
No log	9.5	342	1.1084	0.5858	1.1084	1.0528
No log	9.5556	344	1.1035	0.5858	1.1035	1.0505
No log	9.6111	346	1.0925	0.6040	1.0925	1.0452
No log	9.6667	348	1.0781	0.6009	1.0781	1.0383
No log	9.7222	350	1.0654	0.6092	1.0654	1.0322
No log	9.7778	352	1.0542	0.6113	1.0542	1.0267
No log	9.8333	354	1.0480	0.6113	1.0480	1.0237
No log	9.8889	356	1.0405	0.6225	1.0405	1.0201
No log	9.9444	358	1.0343	0.6166	1.0343	1.0170
No log	10.0	360	1.0323	0.6166	1.0323	1.0160

Framework versions

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