ArabicNewSplits5_FineTuningAraBERT_run3_AugV5_k7_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: 0.9680
• Qwk: 0.6819
• Mse: 0.9680
• Rmse: 0.9839

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	0.0571	2	2.2490	0.0081	2.2490	1.4997
No log	0.1143	4	1.4130	0.1915	1.4130	1.1887
No log	0.1714	6	1.5537	0.0639	1.5537	1.2465
No log	0.2286	8	1.5720	0.0905	1.5720	1.2538
No log	0.2857	10	1.5267	0.1134	1.5267	1.2356
No log	0.3429	12	1.3625	0.2058	1.3625	1.1673
No log	0.4	14	1.2899	0.2867	1.2899	1.1357
No log	0.4571	16	1.2404	0.2733	1.2404	1.1137
No log	0.5143	18	1.2122	0.2602	1.2122	1.1010
No log	0.5714	20	1.0804	0.4301	1.0804	1.0394
No log	0.6286	22	1.0621	0.4900	1.0621	1.0306
No log	0.6857	24	1.0153	0.4819	1.0153	1.0076
No log	0.7429	26	1.0078	0.5316	1.0078	1.0039
No log	0.8	28	0.9769	0.5433	0.9769	0.9884
No log	0.8571	30	1.0173	0.5365	1.0173	1.0086
No log	0.9143	32	0.9723	0.5258	0.9723	0.9861
No log	0.9714	34	0.9089	0.6059	0.9089	0.9534
No log	1.0286	36	0.9087	0.5980	0.9087	0.9532
No log	1.0857	38	0.8973	0.6153	0.8973	0.9473
No log	1.1429	40	0.8914	0.6006	0.8914	0.9441
No log	1.2	42	0.9807	0.5826	0.9807	0.9903
No log	1.2571	44	1.2304	0.5653	1.2304	1.1092
No log	1.3143	46	1.4200	0.4748	1.4200	1.1916
No log	1.3714	48	1.2233	0.5547	1.2233	1.1060
No log	1.4286	50	0.9527	0.5890	0.9527	0.9761
No log	1.4857	52	0.9411	0.5953	0.9411	0.9701
No log	1.5429	54	1.1171	0.5604	1.1171	1.0570
No log	1.6	56	1.4986	0.4614	1.4986	1.2242
No log	1.6571	58	1.5859	0.4472	1.5859	1.2593
No log	1.7143	60	1.4430	0.4710	1.4430	1.2013
No log	1.7714	62	1.0928	0.5547	1.0928	1.0454
No log	1.8286	64	0.8641	0.6353	0.8641	0.9296
No log	1.8857	66	0.8243	0.6050	0.8243	0.9079
No log	1.9429	68	0.8214	0.6319	0.8214	0.9063
No log	2.0	70	0.8469	0.6335	0.8469	0.9203
No log	2.0571	72	1.0465	0.6106	1.0465	1.0230
No log	2.1143	74	1.1546	0.5993	1.1546	1.0745
No log	2.1714	76	1.0616	0.6193	1.0616	1.0303
No log	2.2286	78	0.8776	0.6447	0.8776	0.9368
No log	2.2857	80	0.8890	0.6629	0.8890	0.9429
No log	2.3429	82	1.0029	0.6151	1.0029	1.0014
No log	2.4	84	1.1391	0.5654	1.1391	1.0673
No log	2.4571	86	1.2507	0.5220	1.2507	1.1184
No log	2.5143	88	1.2973	0.5338	1.2973	1.1390
No log	2.5714	90	1.5006	0.5302	1.5006	1.2250
No log	2.6286	92	1.5107	0.5261	1.5107	1.2291
No log	2.6857	94	1.2257	0.5669	1.2257	1.1071
No log	2.7429	96	1.0778	0.5931	1.0778	1.0382
No log	2.8	98	1.1752	0.5589	1.1752	1.0841
No log	2.8571	100	1.3097	0.5097	1.3097	1.1444
No log	2.9143	102	1.5295	0.4882	1.5295	1.2367
No log	2.9714	104	1.6401	0.4673	1.6401	1.2807
No log	3.0286	106	1.4243	0.5052	1.4243	1.1934
No log	3.0857	108	0.9593	0.6320	0.9593	0.9795
No log	3.1429	110	0.6844	0.6872	0.6844	0.8273
No log	3.2	112	0.6907	0.6357	0.6907	0.8311
No log	3.2571	114	0.6998	0.6669	0.6998	0.8366
No log	3.3143	116	0.8310	0.6876	0.8310	0.9116
No log	3.3714	118	1.2011	0.5902	1.2011	1.0959
No log	3.4286	120	1.4426	0.5401	1.4426	1.2011
No log	3.4857	122	1.4260	0.5578	1.4260	1.1942
No log	3.5429	124	1.1836	0.6172	1.1836	1.0879
No log	3.6	126	0.9001	0.6888	0.9001	0.9487
No log	3.6571	128	0.8103	0.6654	0.8103	0.9001
No log	3.7143	130	0.8464	0.6663	0.8464	0.9200
No log	3.7714	132	1.0390	0.6243	1.0390	1.0193
No log	3.8286	134	1.3695	0.5501	1.3695	1.1702
No log	3.8857	136	1.5465	0.5021	1.5465	1.2436
No log	3.9429	138	1.5812	0.4996	1.5812	1.2575
No log	4.0	140	1.4851	0.5108	1.4851	1.2187
No log	4.0571	142	1.2196	0.5754	1.2196	1.1043
No log	4.1143	144	0.9484	0.6592	0.9484	0.9739
No log	4.1714	146	0.8287	0.6529	0.8287	0.9103
No log	4.2286	148	0.8552	0.6885	0.8552	0.9248
No log	4.2857	150	1.0378	0.6458	1.0378	1.0187
No log	4.3429	152	1.3431	0.5504	1.3431	1.1589
No log	4.4	154	1.6287	0.5079	1.6287	1.2762
No log	4.4571	156	1.7172	0.5068	1.7172	1.3104
No log	4.5143	158	1.5507	0.5193	1.5507	1.2453
No log	4.5714	160	1.3913	0.5503	1.3913	1.1795
No log	4.6286	162	1.1877	0.5953	1.1877	1.0898
No log	4.6857	164	1.0987	0.6048	1.0987	1.0482
No log	4.7429	166	1.1795	0.5837	1.1795	1.0861
No log	4.8	168	1.2932	0.5436	1.2932	1.1372
No log	4.8571	170	1.3683	0.5584	1.3683	1.1697
No log	4.9143	172	1.4568	0.5109	1.4568	1.2070
No log	4.9714	174	1.5100	0.5175	1.5100	1.2288
No log	5.0286	176	1.5568	0.5193	1.5568	1.2477
No log	5.0857	178	1.4193	0.5418	1.4193	1.1913
No log	5.1429	180	1.1237	0.6323	1.1237	1.0601
No log	5.2	182	0.8949	0.6915	0.8949	0.9460
No log	5.2571	184	0.7823	0.6783	0.7823	0.8845
No log	5.3143	186	0.8138	0.6830	0.8138	0.9021
No log	5.3714	188	0.9928	0.6758	0.9928	0.9964
No log	5.4286	190	1.2301	0.5671	1.2301	1.1091
No log	5.4857	192	1.2610	0.5430	1.2610	1.1229
No log	5.5429	194	1.1635	0.5820	1.1635	1.0787
No log	5.6	196	0.9763	0.6644	0.9763	0.9881
No log	5.6571	198	0.8764	0.6723	0.8764	0.9362
No log	5.7143	200	0.9051	0.6810	0.9051	0.9514
No log	5.7714	202	0.9472	0.6756	0.9472	0.9732
No log	5.8286	204	0.9874	0.6639	0.9874	0.9937
No log	5.8857	206	1.0225	0.6463	1.0225	1.0112
No log	5.9429	208	0.9572	0.6639	0.9572	0.9784
No log	6.0	210	0.9678	0.6639	0.9678	0.9838
No log	6.0571	212	0.9888	0.6647	0.9888	0.9944
No log	6.1143	214	0.9671	0.6837	0.9671	0.9834
No log	6.1714	216	0.9130	0.6979	0.9130	0.9555
No log	6.2286	218	0.8362	0.6822	0.8362	0.9145
No log	6.2857	220	0.8291	0.6759	0.8291	0.9106
No log	6.3429	222	0.7888	0.6838	0.7888	0.8881
No log	6.4	224	0.7752	0.6765	0.7752	0.8805
No log	6.4571	226	0.8227	0.6908	0.8227	0.9070
No log	6.5143	228	0.8503	0.6871	0.8503	0.9221
No log	6.5714	230	0.9257	0.6779	0.9257	0.9621
No log	6.6286	232	1.0352	0.6273	1.0352	1.0175
No log	6.6857	234	1.1232	0.5814	1.1232	1.0598
No log	6.7429	236	1.1512	0.5763	1.1512	1.0729
No log	6.8	238	1.1169	0.5972	1.1169	1.0568
No log	6.8571	240	1.0031	0.6422	1.0031	1.0015
No log	6.9143	242	0.8846	0.6833	0.8846	0.9406
No log	6.9714	244	0.8535	0.6957	0.8535	0.9239
No log	7.0286	246	0.8401	0.7007	0.8401	0.9166
No log	7.0857	248	0.8594	0.6728	0.8594	0.9271
No log	7.1429	250	0.9658	0.6543	0.9658	0.9828
No log	7.2	252	1.0859	0.5995	1.0859	1.0421
No log	7.2571	254	1.1681	0.5956	1.1681	1.0808
No log	7.3143	256	1.1578	0.5783	1.1578	1.0760
No log	7.3714	258	1.0660	0.6118	1.0660	1.0325
No log	7.4286	260	0.9653	0.6660	0.9653	0.9825
No log	7.4857	262	0.8816	0.6845	0.8816	0.9389
No log	7.5429	264	0.8301	0.6879	0.8301	0.9111
No log	7.6	266	0.8021	0.6923	0.8021	0.8956
No log	7.6571	268	0.8206	0.6957	0.8206	0.9059
No log	7.7143	270	0.8751	0.6801	0.8751	0.9355
No log	7.7714	272	0.9044	0.6832	0.9044	0.9510
No log	7.8286	274	0.9429	0.6653	0.9429	0.9710
No log	7.8857	276	0.9875	0.6671	0.9875	0.9937
No log	7.9429	278	0.9992	0.6752	0.9992	0.9996
No log	8.0	280	0.9626	0.6538	0.9626	0.9811
No log	8.0571	282	0.9302	0.6754	0.9302	0.9645
No log	8.1143	284	0.8812	0.6862	0.8812	0.9387
No log	8.1714	286	0.8269	0.7024	0.8269	0.9093
No log	8.2286	288	0.8181	0.7024	0.8181	0.9045
No log	8.2857	290	0.8524	0.6925	0.8524	0.9232
No log	8.3429	292	0.8874	0.6749	0.8874	0.9420
No log	8.4	294	0.9401	0.6635	0.9401	0.9696
No log	8.4571	296	0.9560	0.6635	0.9560	0.9778
No log	8.5143	298	0.9487	0.6635	0.9487	0.9740
No log	8.5714	300	0.9160	0.6511	0.9160	0.9571
No log	8.6286	302	0.8961	0.6785	0.8961	0.9466
No log	8.6857	304	0.8817	0.6785	0.8817	0.9390
No log	8.7429	306	0.8454	0.6794	0.8454	0.9195
No log	8.8	308	0.8175	0.6838	0.8175	0.9042
No log	8.8571	310	0.8016	0.7024	0.8016	0.8953
No log	8.9143	312	0.7950	0.7024	0.7950	0.8916
No log	8.9714	314	0.7910	0.7024	0.7910	0.8894
No log	9.0286	316	0.7947	0.7024	0.7947	0.8914
No log	9.0857	318	0.8151	0.6925	0.8151	0.9028
No log	9.1429	320	0.8515	0.6925	0.8515	0.9228
No log	9.2	322	0.8975	0.6849	0.8975	0.9474
No log	9.2571	324	0.9468	0.6969	0.9468	0.9730
No log	9.3143	326	1.0020	0.6819	1.0020	1.0010
No log	9.3714	328	1.0505	0.6656	1.0505	1.0250
No log	9.4286	330	1.0687	0.6455	1.0687	1.0338
No log	9.4857	332	1.0746	0.6199	1.0746	1.0366
No log	9.5429	334	1.0664	0.6212	1.0664	1.0327
No log	9.6	336	1.0562	0.6455	1.0562	1.0277
No log	9.6571	338	1.0390	0.6656	1.0390	1.0193
No log	9.7143	340	1.0237	0.6745	1.0237	1.0118
No log	9.7714	342	1.0066	0.6802	1.0066	1.0033
No log	9.8286	344	0.9903	0.6819	0.9903	0.9951
No log	9.8857	346	0.9772	0.6819	0.9772	0.9885
No log	9.9429	348	0.9707	0.6819	0.9707	0.9852
No log	10.0	350	0.9680	0.6819	0.9680	0.9839

Framework versions

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