ArabicNewSplits6_FineTuningAraBERT_run1_AugV5_k2_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: 1.0588
• Qwk: 0.6040
• Mse: 1.0588
• Rmse: 1.0290

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	0.1818	2	2.4226	0.0252	2.4226	1.5565
No log	0.3636	4	1.5601	0.2288	1.5601	1.2490
No log	0.5455	6	1.5114	0.1014	1.5114	1.2294
No log	0.7273	8	1.6684	0.1797	1.6684	1.2917
No log	0.9091	10	1.8126	0.3272	1.8126	1.3463
No log	1.0909	12	1.7276	0.3300	1.7276	1.3144
No log	1.2727	14	1.6557	0.3762	1.6557	1.2868
No log	1.4545	16	1.4907	0.2748	1.4907	1.2209
No log	1.6364	18	1.3493	0.0894	1.3493	1.1616
No log	1.8182	20	1.3178	0.1909	1.3178	1.1480
No log	2.0	22	1.3307	0.2952	1.3307	1.1536
No log	2.1818	24	1.3477	0.3603	1.3477	1.1609
No log	2.3636	26	1.3950	0.4292	1.3950	1.1811
No log	2.5455	28	1.2461	0.3977	1.2461	1.1163
No log	2.7273	30	1.1667	0.4050	1.1667	1.0802
No log	2.9091	32	1.1903	0.4424	1.1903	1.0910
No log	3.0909	34	1.0399	0.4559	1.0399	1.0198
No log	3.2727	36	0.9236	0.4815	0.9236	0.9610
No log	3.4545	38	0.8964	0.5521	0.8964	0.9468
No log	3.6364	40	0.8909	0.5127	0.8909	0.9439
No log	3.8182	42	1.1592	0.4744	1.1592	1.0767
No log	4.0	44	1.4247	0.4414	1.4247	1.1936
No log	4.1818	46	1.3650	0.4636	1.3650	1.1683
No log	4.3636	48	1.0894	0.5018	1.0894	1.0437
No log	4.5455	50	0.9799	0.5020	0.9799	0.9899
No log	4.7273	52	0.9778	0.5101	0.9778	0.9888
No log	4.9091	54	1.0350	0.5402	1.0350	1.0174
No log	5.0909	56	1.0077	0.5317	1.0077	1.0038
No log	5.2727	58	0.9646	0.5618	0.9646	0.9821
No log	5.4545	60	0.9008	0.6083	0.9008	0.9491
No log	5.6364	62	0.8645	0.6132	0.8645	0.9298
No log	5.8182	64	0.8856	0.6201	0.8856	0.9411
No log	6.0	66	0.9473	0.6269	0.9473	0.9733
No log	6.1818	68	1.1156	0.5386	1.1156	1.0562
No log	6.3636	70	1.1980	0.5432	1.1980	1.0945
No log	6.5455	72	1.1144	0.5417	1.1144	1.0557
No log	6.7273	74	1.0420	0.5709	1.0420	1.0208
No log	6.9091	76	1.0775	0.5585	1.0775	1.0380
No log	7.0909	78	1.0694	0.5744	1.0694	1.0341
No log	7.2727	80	1.1322	0.5475	1.1322	1.0640
No log	7.4545	82	1.1752	0.5265	1.1752	1.0841
No log	7.6364	84	1.1552	0.5294	1.1552	1.0748
No log	7.8182	86	1.0646	0.5837	1.0646	1.0318
No log	8.0	88	0.9982	0.5938	0.9982	0.9991
No log	8.1818	90	0.9988	0.5938	0.9988	0.9994
No log	8.3636	92	1.0455	0.5980	1.0455	1.0225
No log	8.5455	94	1.1154	0.5799	1.1154	1.0561
No log	8.7273	96	1.1372	0.5710	1.1372	1.0664
No log	8.9091	98	1.1507	0.5574	1.1507	1.0727
No log	9.0909	100	1.1220	0.5948	1.1220	1.0593
No log	9.2727	102	1.0955	0.5948	1.0955	1.0467
No log	9.4545	104	1.0943	0.5948	1.0943	1.0461
No log	9.6364	106	1.0724	0.5948	1.0724	1.0356
No log	9.8182	108	1.0635	0.5948	1.0635	1.0313
No log	10.0	110	1.0588	0.6040	1.0588	1.0290

Framework versions

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