ArabicNewSplits6_WithDuplicationsForScore5_FineTuningAraBERT_run3_AugV5_k5_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: 1.3097
• Qwk: 0.5708
• Mse: 1.3097
• Rmse: 1.1444

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	0.0952	2	2.2127	0.0505	2.2127	1.4875
No log	0.1905	4	1.5235	0.1352	1.5235	1.2343
No log	0.2857	6	1.5569	0.2115	1.5569	1.2477
No log	0.3810	8	1.6518	0.1952	1.6518	1.2852
No log	0.4762	10	1.6372	0.3114	1.6372	1.2795
No log	0.5714	12	1.5877	0.3147	1.5877	1.2600
No log	0.6667	14	1.5221	0.3678	1.5221	1.2337
No log	0.7619	16	1.5477	0.4165	1.5477	1.2441
No log	0.8571	18	1.4099	0.4027	1.4099	1.1874
No log	0.9524	20	1.3755	0.3988	1.3755	1.1728
No log	1.0476	22	1.4916	0.4315	1.4916	1.2213
No log	1.1429	24	1.5353	0.4262	1.5353	1.2391
No log	1.2381	26	1.5557	0.4225	1.5557	1.2473
No log	1.3333	28	1.4451	0.4281	1.4451	1.2021
No log	1.4286	30	1.3278	0.4405	1.3278	1.1523
No log	1.5238	32	1.3095	0.4308	1.3095	1.1444
No log	1.6190	34	1.2677	0.5006	1.2677	1.1259
No log	1.7143	36	1.4050	0.4463	1.4050	1.1853
No log	1.8095	38	1.3605	0.4727	1.3605	1.1664
No log	1.9048	40	1.1406	0.5189	1.1406	1.0680
No log	2.0	42	1.0212	0.4917	1.0212	1.0105
No log	2.0952	44	0.9574	0.5412	0.9574	0.9785
No log	2.1905	46	0.9566	0.5159	0.9566	0.9781
No log	2.2857	48	1.0169	0.5172	1.0169	1.0084
No log	2.3810	50	1.1335	0.5537	1.1335	1.0646
No log	2.4762	52	1.2471	0.5292	1.2471	1.1167
No log	2.5714	54	1.1569	0.5397	1.1569	1.0756
No log	2.6667	56	1.1601	0.5650	1.1601	1.0771
No log	2.7619	58	1.1899	0.5462	1.1899	1.0908
No log	2.8571	60	1.1537	0.5821	1.1537	1.0741
No log	2.9524	62	1.0254	0.5955	1.0254	1.0126
No log	3.0476	64	1.1521	0.5868	1.1521	1.0734
No log	3.1429	66	1.5385	0.5666	1.5385	1.2404
No log	3.2381	68	1.5761	0.5169	1.5761	1.2554
No log	3.3333	70	1.3900	0.5249	1.3900	1.1790
No log	3.4286	72	1.3083	0.5657	1.3083	1.1438
No log	3.5238	74	1.2615	0.5726	1.2615	1.1232
No log	3.6190	76	1.2670	0.5838	1.2670	1.1256
No log	3.7143	78	1.4406	0.5584	1.4406	1.2002
No log	3.8095	80	1.4132	0.5542	1.4132	1.1888
No log	3.9048	82	1.1833	0.5573	1.1833	1.0878
No log	4.0	84	1.1200	0.5704	1.1200	1.0583
No log	4.0952	86	1.3352	0.5368	1.3352	1.1555
No log	4.1905	88	1.5819	0.5206	1.5819	1.2577
No log	4.2857	90	1.4818	0.5266	1.4818	1.2173
No log	4.3810	92	1.3903	0.5339	1.3903	1.1791
No log	4.4762	94	1.0930	0.5905	1.0930	1.0455
No log	4.5714	96	0.8030	0.6417	0.8030	0.8961
No log	4.6667	98	0.7705	0.6524	0.7705	0.8778
No log	4.7619	100	0.9603	0.6417	0.9603	0.9799
No log	4.8571	102	1.1692	0.5668	1.1692	1.0813
No log	4.9524	104	1.3011	0.5423	1.3011	1.1406
No log	5.0476	106	1.6031	0.5345	1.6031	1.2661
No log	5.1429	108	1.7746	0.5219	1.7746	1.3322
No log	5.2381	110	1.7425	0.5441	1.7425	1.3200
No log	5.3333	112	1.6005	0.5568	1.6005	1.2651
No log	5.4286	114	1.4668	0.5596	1.4668	1.2111
No log	5.5238	116	1.4628	0.5612	1.4628	1.2094
No log	5.6190	118	1.6692	0.5449	1.6692	1.2920
No log	5.7143	120	1.8710	0.5256	1.8710	1.3678
No log	5.8095	122	1.6790	0.5531	1.6790	1.2958
No log	5.9048	124	1.2319	0.5688	1.2319	1.1099
No log	6.0	126	0.8256	0.6510	0.8256	0.9086
No log	6.0952	128	0.7282	0.6860	0.7282	0.8533
No log	6.1905	130	0.7903	0.6496	0.7903	0.8890
No log	6.2857	132	1.0661	0.6160	1.0661	1.0325
No log	6.3810	134	1.5196	0.5501	1.5196	1.2327
No log	6.4762	136	1.7253	0.5230	1.7253	1.3135
No log	6.5714	138	1.6472	0.5400	1.6472	1.2834
No log	6.6667	140	1.4409	0.5606	1.4409	1.2004
No log	6.7619	142	1.3506	0.5630	1.3506	1.1622
No log	6.8571	144	1.2583	0.6054	1.2583	1.1217
No log	6.9524	146	1.2260	0.6189	1.2260	1.1072
No log	7.0476	148	1.1213	0.6346	1.1213	1.0589
No log	7.1429	150	1.0366	0.6516	1.0366	1.0182
No log	7.2381	152	1.0625	0.6387	1.0625	1.0308
No log	7.3333	154	1.2089	0.6270	1.2089	1.0995
No log	7.4286	156	1.2884	0.6237	1.2884	1.1351
No log	7.5238	158	1.3527	0.6029	1.3527	1.1631
No log	7.6190	160	1.3479	0.6029	1.3479	1.1610
No log	7.7143	162	1.2253	0.6361	1.2253	1.1069
No log	7.8095	164	1.1668	0.6230	1.1668	1.0802
No log	7.9048	166	1.2054	0.6305	1.2054	1.0979
No log	8.0	168	1.3180	0.5986	1.3180	1.1480
No log	8.0952	170	1.3975	0.5918	1.3975	1.1822
No log	8.1905	172	1.3612	0.5986	1.3612	1.1667
No log	8.2857	174	1.2362	0.5984	1.2362	1.1119
No log	8.3810	176	1.1251	0.6282	1.1251	1.0607
No log	8.4762	178	1.0428	0.6559	1.0428	1.0212
No log	8.5714	180	1.0634	0.6374	1.0634	1.0312
No log	8.6667	182	1.1539	0.6311	1.1539	1.0742
No log	8.7619	184	1.2778	0.5956	1.2778	1.1304
No log	8.8571	186	1.3875	0.5883	1.3875	1.1779
No log	8.9524	188	1.4499	0.5804	1.4499	1.2041
No log	9.0476	190	1.4359	0.5796	1.4359	1.1983
No log	9.1429	192	1.4043	0.5824	1.4043	1.1850
No log	9.2381	194	1.3707	0.5700	1.3707	1.1708
No log	9.3333	196	1.3398	0.5700	1.3398	1.1575
No log	9.4286	198	1.3092	0.5708	1.3092	1.1442
No log	9.5238	200	1.2941	0.5921	1.2941	1.1376
No log	9.6190	202	1.2865	0.5921	1.2865	1.1342
No log	9.7143	204	1.2945	0.5782	1.2945	1.1377
No log	9.8095	206	1.3076	0.5708	1.3076	1.1435
No log	9.9048	208	1.3110	0.5708	1.3110	1.1450
No log	10.0	210	1.3097	0.5708	1.3097	1.1444

Framework versions

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