Arabic_FineTuningAraBERT_AugV0_k1_task1_organization_fold1

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: 0.6040
• Qwk: 0.6847
• Mse: 0.6040
• Rmse: 0.7772

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	0.125	2	3.7867	-0.0180	3.7867	1.9459
No log	0.25	4	1.9998	0.2320	1.9998	1.4141
No log	0.375	6	1.0711	-0.0396	1.0711	1.0350
No log	0.5	8	0.9376	0.0982	0.9376	0.9683
No log	0.625	10	0.7792	0.2125	0.7792	0.8827
No log	0.75	12	0.5459	0.4731	0.5459	0.7389
No log	0.875	14	0.5198	0.51	0.5198	0.7210
No log	1.0	16	0.5273	0.5517	0.5273	0.7262
No log	1.125	18	0.5321	0.6224	0.5321	0.7295
No log	1.25	20	0.5241	0.6667	0.5241	0.7240
No log	1.375	22	0.4927	0.6486	0.4927	0.7020
No log	1.5	24	0.5528	0.5692	0.5528	0.7435
No log	1.625	26	0.4789	0.6889	0.4789	0.6920
No log	1.75	28	0.6811	0.5395	0.6811	0.8253
No log	1.875	30	1.0119	0.3772	1.0119	1.0059
No log	2.0	32	0.8998	0.3784	0.8998	0.9486
No log	2.125	34	0.5753	0.5070	0.5753	0.7585
No log	2.25	36	0.4745	0.5767	0.4745	0.6888
No log	2.375	38	0.5193	0.6147	0.5193	0.7206
No log	2.5	40	0.4825	0.5767	0.4825	0.6946
No log	2.625	42	0.4648	0.6182	0.4648	0.6818
No log	2.75	44	0.5393	0.7072	0.5393	0.7343
No log	2.875	46	0.5297	0.7220	0.5297	0.7278
No log	3.0	48	0.4946	0.7220	0.4946	0.7033
No log	3.125	50	0.4299	0.7	0.4299	0.6557
No log	3.25	52	0.4385	0.6667	0.4385	0.6622
No log	3.375	54	0.4424	0.6667	0.4424	0.6651
No log	3.5	56	0.4762	0.7	0.4762	0.6901
No log	3.625	58	0.5567	0.7	0.5567	0.7462
No log	3.75	60	0.5485	0.7	0.5485	0.7406
No log	3.875	62	0.5083	0.6290	0.5083	0.7130
No log	4.0	64	0.4976	0.6084	0.4976	0.7054
No log	4.125	66	0.5228	0.7	0.5228	0.7231
No log	4.25	68	0.4997	0.7	0.4997	0.7069
No log	4.375	70	0.5183	0.7	0.5183	0.7200
No log	4.5	72	0.6043	0.7016	0.6043	0.7774
No log	4.625	74	0.6707	0.7016	0.6707	0.8190
No log	4.75	76	0.6478	0.7016	0.6478	0.8048
No log	4.875	78	0.5690	0.6769	0.5690	0.7543
No log	5.0	80	0.5403	0.6263	0.5403	0.7350
No log	5.125	82	0.5245	0.7050	0.5245	0.7242
No log	5.25	84	0.5001	0.6978	0.5001	0.7072
No log	5.375	86	0.4801	0.6978	0.4801	0.6929
No log	5.5	88	0.4978	0.7287	0.4978	0.7055
No log	5.625	90	0.5501	0.7016	0.5501	0.7417
No log	5.75	92	0.6042	0.7219	0.6042	0.7773
No log	5.875	94	0.5626	0.7016	0.5626	0.7501
No log	6.0	96	0.5092	0.7050	0.5092	0.7136
No log	6.125	98	0.5001	0.6288	0.5001	0.7072
No log	6.25	100	0.4953	0.6288	0.4953	0.7038
No log	6.375	102	0.5378	0.7287	0.5378	0.7333
No log	6.5	104	0.6240	0.6789	0.6240	0.7899
No log	6.625	106	0.7492	0.6991	0.7492	0.8656
No log	6.75	108	0.8331	0.6415	0.8331	0.9127
No log	6.875	110	0.8239	0.6415	0.8239	0.9077
No log	7.0	112	0.7363	0.6991	0.7363	0.8581
No log	7.125	114	0.6138	0.6606	0.6138	0.7835
No log	7.25	116	0.5381	0.6573	0.5381	0.7336
No log	7.375	118	0.5289	0.6978	0.5289	0.7272
No log	7.5	120	0.5491	0.6784	0.5491	0.7410
No log	7.625	122	0.6250	0.6789	0.6250	0.7906
No log	7.75	124	0.7445	0.6991	0.7445	0.8629
No log	7.875	126	0.7655	0.6991	0.7655	0.8749
No log	8.0	128	0.7507	0.6991	0.7507	0.8664
No log	8.125	130	0.7196	0.6991	0.7196	0.8483
No log	8.25	132	0.6492	0.6975	0.6492	0.8057
No log	8.375	134	0.6000	0.6899	0.6000	0.7746
No log	8.5	136	0.5639	0.6899	0.5639	0.7509
No log	8.625	138	0.5275	0.7	0.5275	0.7263
No log	8.75	140	0.5147	0.7050	0.5147	0.7174
No log	8.875	142	0.5215	0.7050	0.5215	0.7221
No log	9.0	144	0.5328	0.6733	0.5328	0.7300
No log	9.125	146	0.5525	0.7016	0.5525	0.7433
No log	9.25	148	0.5649	0.6847	0.5649	0.7516
No log	9.375	150	0.5844	0.6847	0.5844	0.7644
No log	9.5	152	0.5954	0.6847	0.5954	0.7716
No log	9.625	154	0.5976	0.6847	0.5976	0.7730
No log	9.75	156	0.5980	0.6847	0.5980	0.7733
No log	9.875	158	0.6022	0.6847	0.6022	0.7760
No log	10.0	160	0.6040	0.6847	0.6040	0.7772

Framework versions

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