Arabic_FineTuningAraBERT_AugV5_k5_task3_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: 0.9938
• Qwk: -0.0820
• Mse: 0.9938
• Rmse: 0.9969

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	0.0769	2	6.4882	0.0120	6.4882	2.5472
No log	0.1538	4	2.8615	0.0763	2.8615	1.6916
No log	0.2308	6	1.2489	0.0	1.2489	1.1175
No log	0.3077	8	1.2975	0.0120	1.2975	1.1391
No log	0.3846	10	1.4121	0.0253	1.4121	1.1883
No log	0.4615	12	1.0061	0.0253	1.0061	1.0030
No log	0.5385	14	0.7697	0.1879	0.7697	0.8773
No log	0.6154	16	1.3628	0.0	1.3628	1.1674
No log	0.6923	18	1.3278	0.0	1.3278	1.1523
No log	0.7692	20	1.0906	0.0	1.0906	1.0443
No log	0.8462	22	0.9415	0.0	0.9415	0.9703
No log	0.9231	24	0.8609	0.0763	0.8609	0.9278
No log	1.0	26	1.0114	0.0120	1.0114	1.0057
No log	1.0769	28	0.8698	0.0120	0.8698	0.9326
No log	1.1538	30	1.0945	-0.1139	1.0945	1.0462
No log	1.2308	32	1.5711	0.0	1.5711	1.2534
No log	1.3077	34	1.4726	0.0	1.4726	1.2135
No log	1.3846	36	1.3741	0.0120	1.3741	1.1722
No log	1.4615	38	1.3272	-0.1139	1.3272	1.1521
No log	1.5385	40	0.8637	-0.4602	0.8637	0.9293
No log	1.6154	42	0.7004	0.0	0.7004	0.8369
No log	1.6923	44	0.7366	0.0	0.7366	0.8583
No log	1.7692	46	0.9411	-0.4275	0.9411	0.9701
No log	1.8462	48	1.3252	0.0120	1.3252	1.1512
No log	1.9231	50	1.5053	0.0	1.5053	1.2269
No log	2.0	52	1.5209	0.0	1.5209	1.2332
No log	2.0769	54	1.3356	0.0	1.3356	1.1557
No log	2.1538	56	0.9869	0.0	0.9869	0.9934
No log	2.2308	58	0.8408	0.1646	0.8408	0.9170
No log	2.3077	60	0.8580	0.0	0.8580	0.9263
No log	2.3846	62	0.9236	0.0	0.9236	0.9611
No log	2.4615	64	0.9641	0.0120	0.9641	0.9819
No log	2.5385	66	0.9209	-0.1139	0.9209	0.9596
No log	2.6154	68	0.8825	-0.4426	0.8825	0.9394
No log	2.6923	70	0.8844	-0.2692	0.8844	0.9404
No log	2.7692	72	0.7791	-0.2791	0.7791	0.8827
No log	2.8462	74	0.7874	-0.2791	0.7874	0.8873
No log	2.9231	76	0.9282	-0.2791	0.9282	0.9634
No log	3.0	78	1.2708	-0.4275	1.2708	1.1273
No log	3.0769	80	1.2567	-0.4426	1.2567	1.1210
No log	3.1538	82	0.8678	-0.2791	0.8678	0.9316
No log	3.2308	84	0.5034	0.4211	0.5034	0.7095
No log	3.3077	86	0.4776	0.4590	0.4776	0.6911
No log	3.3846	88	0.5597	0.2443	0.5597	0.7481
No log	3.4615	90	0.9531	0.1239	0.9531	0.9763
No log	3.5385	92	1.4142	-0.2222	1.4142	1.1892
No log	3.6154	94	1.4356	-0.1058	1.4356	1.1982
No log	3.6923	96	1.1902	-0.1074	1.1902	1.0909
No log	3.7692	98	0.8565	0.1239	0.8565	0.9255
No log	3.8462	100	0.5664	0.1239	0.5664	0.7526
No log	3.9231	102	0.4910	0.4211	0.4910	0.7007
No log	4.0	104	0.6272	-0.2791	0.6272	0.7920
No log	4.0769	106	0.8063	-0.2692	0.8063	0.8979
No log	4.1538	108	0.9651	-0.2692	0.9651	0.9824
No log	4.2308	110	1.1817	-0.2595	1.1817	1.0871
No log	4.3077	112	1.2166	-0.2571	1.2166	1.1030
No log	4.3846	114	1.0163	-0.4602	1.0163	1.0081
No log	4.4615	116	0.9236	-0.2692	0.9236	0.9611
No log	4.5385	118	0.9074	-0.2692	0.9074	0.9526
No log	4.6154	120	0.8761	-0.2692	0.8761	0.9360
No log	4.6923	122	0.9739	-0.2595	0.9739	0.9869
No log	4.7692	124	1.0063	-0.2571	1.0063	1.0032
No log	4.8462	126	1.0867	0.0403	1.0867	1.0425
No log	4.9231	128	1.0136	0.0403	1.0136	1.0068
No log	5.0	130	0.9020	0.2443	0.9020	0.9497
No log	5.0769	132	0.8408	0.2443	0.8408	0.9170
No log	5.1538	134	1.0709	0.0403	1.0709	1.0348
No log	5.2308	136	1.1822	0.0403	1.1822	1.0873
No log	5.3077	138	0.9413	0.0571	0.9413	0.9702
No log	5.3846	140	0.7544	0.1270	0.7544	0.8686
No log	5.4615	142	0.7863	0.2443	0.7863	0.8867
No log	5.5385	144	1.1251	0.0403	1.1251	1.0607
No log	5.6154	146	1.2707	0.0403	1.2707	1.1273
No log	5.6923	148	1.1481	0.0403	1.1481	1.0715
No log	5.7692	150	1.1328	0.0403	1.1328	1.0644
No log	5.8462	152	1.2027	0.0403	1.2027	1.0967
No log	5.9231	154	1.2689	0.0403	1.2689	1.1265
No log	6.0	156	1.2094	0.0403	1.2094	1.0997
No log	6.0769	158	0.9554	0.0403	0.9554	0.9774
No log	6.1538	160	0.7977	0.2443	0.7977	0.8932
No log	6.2308	162	0.8738	0.0403	0.8738	0.9348
No log	6.3077	164	0.9806	0.0403	0.9806	0.9903
No log	6.3846	166	0.9343	0.0403	0.9343	0.9666
No log	6.4615	168	0.9511	0.0403	0.9511	0.9753
No log	6.5385	170	1.0951	0.0403	1.0951	1.0465
No log	6.6154	172	1.2844	0.0403	1.2844	1.1333
No log	6.6923	174	1.1801	0.0403	1.1801	1.0863
No log	6.7692	176	0.9290	0.2443	0.9290	0.9638
No log	6.8462	178	0.8739	-0.0820	0.8739	0.9348
No log	6.9231	180	0.9441	-0.0820	0.9441	0.9716
No log	7.0	182	1.1352	0.0571	1.1352	1.0655
No log	7.0769	184	1.2470	0.0403	1.2470	1.1167
No log	7.1538	186	1.1198	-0.2595	1.1198	1.0582
No log	7.2308	188	0.9832	-0.0820	0.9832	0.9916
No log	7.3077	190	0.8924	-0.2692	0.8924	0.9447
No log	7.3846	192	0.9152	-0.2692	0.9152	0.9566
No log	7.4615	194	1.0180	-0.0708	1.0180	1.0090
No log	7.5385	196	1.1520	-0.2595	1.1520	1.0733
No log	7.6154	198	1.1170	-0.2595	1.1170	1.0569
No log	7.6923	200	1.0034	-0.0708	1.0034	1.0017
No log	7.7692	202	0.9057	-0.0708	0.9057	0.9517
No log	7.8462	204	0.9190	-0.0708	0.9190	0.9587
No log	7.9231	206	0.9038	-0.0708	0.9038	0.9507
No log	8.0	208	0.8591	-0.0708	0.8591	0.9269
No log	8.0769	210	0.8657	-0.0820	0.8657	0.9304
No log	8.1538	212	0.9487	-0.0820	0.9487	0.9740
No log	8.2308	214	1.0921	0.0403	1.0921	1.0450
No log	8.3077	216	1.1481	0.0403	1.1481	1.0715
No log	8.3846	218	1.0795	0.0403	1.0795	1.0390
No log	8.4615	220	0.9810	-0.0820	0.9810	0.9905
No log	8.5385	222	0.8751	-0.0820	0.8751	0.9355
No log	8.6154	224	0.8409	-0.0820	0.8409	0.9170
No log	8.6923	226	0.8786	-0.0820	0.8786	0.9373
No log	8.7692	228	0.9480	-0.0820	0.9480	0.9736
No log	8.8462	230	1.0155	-0.0820	1.0155	1.0077
No log	8.9231	232	1.0158	-0.0820	1.0158	1.0079
No log	9.0	234	1.0166	-0.0820	1.0166	1.0083
No log	9.0769	236	1.0048	-0.0820	1.0048	1.0024
No log	9.1538	238	1.0121	-0.0820	1.0121	1.0060
No log	9.2308	240	1.0128	-0.0820	1.0128	1.0064
No log	9.3077	242	1.0097	-0.0820	1.0097	1.0048
No log	9.3846	244	1.0094	-0.0820	1.0094	1.0047
No log	9.4615	246	1.0006	-0.0820	1.0006	1.0003
No log	9.5385	248	1.0092	-0.0820	1.0092	1.0046
No log	9.6154	250	1.0080	-0.0820	1.0080	1.0040
No log	9.6923	252	1.0038	-0.0820	1.0038	1.0019
No log	9.7692	254	0.9971	-0.0820	0.9971	0.9985
No log	9.8462	256	0.9948	-0.0820	0.9948	0.9974
No log	9.9231	258	0.9944	-0.0820	0.9944	0.9972
No log	10.0	260	0.9938	-0.0820	0.9938	0.9969

Framework versions

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