ArabicNewSplits6_WithDuplicationsForScore5_FineTuningAraBERT_run2_AugV5_k3_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: 1.4200
• Qwk: 0.4220
• Mse: 1.4200
• Rmse: 1.1916

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	0.1053	2	5.0183	-0.0323	5.0183	2.2402
No log	0.2105	4	2.7201	0.0765	2.7201	1.6493
No log	0.3158	6	1.5771	0.0820	1.5771	1.2558
No log	0.4211	8	1.1804	0.2459	1.1804	1.0865
No log	0.5263	10	1.2319	0.1732	1.2319	1.1099
No log	0.6316	12	1.4421	0.0994	1.4421	1.2009
No log	0.7368	14	1.4482	0.0935	1.4482	1.2034
No log	0.8421	16	1.6370	0.3195	1.6370	1.2794
No log	0.9474	18	1.7928	0.1419	1.7928	1.3390
No log	1.0526	20	1.6610	0.1035	1.6610	1.2888
No log	1.1579	22	1.5686	0.2914	1.5686	1.2524
No log	1.2632	24	1.1584	0.2128	1.1584	1.0763
No log	1.3684	26	1.3211	0.1833	1.3211	1.1494
No log	1.4737	28	1.1913	0.2486	1.1913	1.0915
No log	1.5789	30	1.0844	0.3229	1.0844	1.0413
No log	1.6842	32	1.3125	0.1936	1.3125	1.1456
No log	1.7895	34	1.3726	0.2429	1.3726	1.1716
No log	1.8947	36	1.2772	0.1135	1.2772	1.1301
No log	2.0	38	1.1581	0.1841	1.1581	1.0761
No log	2.1053	40	1.0982	0.3018	1.0982	1.0480
No log	2.2105	42	1.2243	0.2384	1.2243	1.1065
No log	2.3158	44	1.2723	0.1478	1.2723	1.1280
No log	2.4211	46	1.1217	0.3117	1.1217	1.0591
No log	2.5263	48	1.0096	0.3300	1.0096	1.0048
No log	2.6316	50	0.9987	0.3536	0.9987	0.9994
No log	2.7368	52	1.0250	0.3970	1.0250	1.0124
No log	2.8421	54	1.0567	0.4691	1.0567	1.0280
No log	2.9474	56	1.0624	0.4677	1.0624	1.0307
No log	3.0526	58	1.0915	0.3421	1.0915	1.0448
No log	3.1579	60	1.2029	0.2905	1.2029	1.0968
No log	3.2632	62	1.2751	0.2385	1.2751	1.1292
No log	3.3684	64	1.1614	0.3735	1.1614	1.0777
No log	3.4737	66	1.1008	0.4324	1.1008	1.0492
No log	3.5789	68	1.2093	0.4230	1.2093	1.0997
No log	3.6842	70	1.1398	0.4605	1.1398	1.0676
No log	3.7895	72	0.9863	0.5238	0.9863	0.9931
No log	3.8947	74	0.8986	0.5252	0.8986	0.9480
No log	4.0	76	1.0674	0.4749	1.0674	1.0332
No log	4.1053	78	1.0757	0.4538	1.0757	1.0372
No log	4.2105	80	1.0394	0.4988	1.0394	1.0195
No log	4.3158	82	0.9434	0.4841	0.9434	0.9713
No log	4.4211	84	0.9186	0.5249	0.9186	0.9584
No log	4.5263	86	0.9716	0.4308	0.9716	0.9857
No log	4.6316	88	1.0992	0.4871	1.0992	1.0484
No log	4.7368	90	1.2037	0.4594	1.2037	1.0971
No log	4.8421	92	1.2619	0.4486	1.2619	1.1233
No log	4.9474	94	1.2964	0.4501	1.2964	1.1386
No log	5.0526	96	1.3820	0.4526	1.3820	1.1756
No log	5.1579	98	1.5322	0.4032	1.5322	1.2378
No log	5.2632	100	1.5755	0.4228	1.5755	1.2552
No log	5.3684	102	1.4931	0.4319	1.4931	1.2219
No log	5.4737	104	1.4401	0.4289	1.4401	1.2001
No log	5.5789	106	1.4916	0.4490	1.4916	1.2213
No log	5.6842	108	1.5628	0.4397	1.5628	1.2501
No log	5.7895	110	1.6021	0.4312	1.6021	1.2657
No log	5.8947	112	1.5574	0.4313	1.5574	1.2480
No log	6.0	114	1.4423	0.4741	1.4423	1.2010
No log	6.1053	116	1.2979	0.4295	1.2979	1.1393
No log	6.2105	118	1.2206	0.3927	1.2206	1.1048
No log	6.3158	120	1.2280	0.3763	1.2280	1.1082
No log	6.4211	122	1.3063	0.4416	1.3063	1.1430
No log	6.5263	124	1.3850	0.4419	1.3850	1.1769
No log	6.6316	126	1.4639	0.4183	1.4639	1.2099
No log	6.7368	128	1.5148	0.4152	1.5148	1.2308
No log	6.8421	130	1.5243	0.4307	1.5243	1.2346
No log	6.9474	132	1.4912	0.4241	1.4912	1.2212
No log	7.0526	134	1.4008	0.3981	1.4008	1.1836
No log	7.1579	136	1.3322	0.3557	1.3322	1.1542
No log	7.2632	138	1.3316	0.3519	1.3316	1.1539
No log	7.3684	140	1.3665	0.4332	1.3665	1.1690
No log	7.4737	142	1.3947	0.4442	1.3947	1.1810
No log	7.5789	144	1.3920	0.4639	1.3920	1.1798
No log	7.6842	146	1.3876	0.4475	1.3876	1.1780
No log	7.7895	148	1.3569	0.4560	1.3569	1.1649
No log	7.8947	150	1.3297	0.4447	1.3297	1.1531
No log	8.0	152	1.3026	0.4430	1.3026	1.1413
No log	8.1053	154	1.3034	0.4346	1.3034	1.1417
No log	8.2105	156	1.3277	0.4540	1.3277	1.1523
No log	8.3158	158	1.3543	0.4423	1.3543	1.1638
No log	8.4211	160	1.3813	0.4194	1.3813	1.1753
No log	8.5263	162	1.3916	0.4194	1.3916	1.1797
No log	8.6316	164	1.3872	0.4194	1.3872	1.1778
No log	8.7368	166	1.3841	0.4158	1.3841	1.1765
No log	8.8421	168	1.3847	0.4158	1.3847	1.1767
No log	8.9474	170	1.3802	0.4352	1.3802	1.1748
No log	9.0526	172	1.3845	0.4447	1.3845	1.1766
No log	9.1579	174	1.3975	0.4525	1.3975	1.1822
No log	9.2632	176	1.4164	0.4220	1.4164	1.1901
No log	9.3684	178	1.4243	0.4220	1.4243	1.1934
No log	9.4737	180	1.4248	0.4380	1.4248	1.1937
No log	9.5789	182	1.4258	0.4380	1.4258	1.1941
No log	9.6842	184	1.4236	0.4220	1.4236	1.1931
No log	9.7895	186	1.4218	0.4220	1.4218	1.1924
No log	9.8947	188	1.4203	0.4220	1.4203	1.1918
No log	10.0	190	1.4200	0.4220	1.4200	1.1916

Framework versions

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