arabert_augmented_only_k1_organization_task1_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: 0.9677
• Qwk: 0.1026
• Mse: 0.9677
• Rmse: 0.9837

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	0.2	2	3.2735	0.0	3.2735	1.8093
No log	0.4	4	1.9420	-0.0038	1.9420	1.3935
No log	0.6	6	1.2781	0.0833	1.2781	1.1305
No log	0.8	8	1.1357	0.2164	1.1357	1.0657
No log	1.0	10	1.3092	0.1003	1.3092	1.1442
No log	1.2	12	1.1508	0.0597	1.1508	1.0728
No log	1.4	14	1.0478	0.0	1.0478	1.0236
No log	1.6	16	1.1473	0.0427	1.1473	1.0711
No log	1.8	18	1.3598	0.0597	1.3598	1.1661
No log	2.0	20	1.4375	0.0413	1.4375	1.1990
No log	2.2	22	1.4395	0.0919	1.4395	1.1998
No log	2.4	24	1.3221	0.0597	1.3221	1.1498
No log	2.6	26	1.2919	0.0597	1.2919	1.1366
No log	2.8	28	1.2743	0.0912	1.2743	1.1288
No log	3.0	30	1.2169	0.0797	1.2169	1.1031
No log	3.2	32	1.1561	0.0797	1.1561	1.0752
No log	3.4	34	1.1205	0.0797	1.1205	1.0585
No log	3.6	36	1.1014	0.0427	1.1014	1.0495
No log	3.8	38	1.1209	0.0427	1.1209	1.0587
No log	4.0	40	1.1519	0.1355	1.1519	1.0732
No log	4.2	42	1.1845	0.1119	1.1845	1.0883
No log	4.4	44	1.2961	0.1667	1.2961	1.1385
No log	4.6	46	1.2551	0.1656	1.2551	1.1203
No log	4.8	48	1.1120	0.1355	1.1120	1.0545
No log	5.0	50	0.9673	0.1355	0.9673	0.9835
No log	5.2	52	0.9367	0.0	0.9367	0.9678
No log	5.4	54	0.9394	0.0	0.9394	0.9692
No log	5.6	56	0.9309	0.0	0.9309	0.9648
No log	5.8	58	0.9198	0.0	0.9198	0.9590
No log	6.0	60	0.9171	0.1026	0.9171	0.9577
No log	6.2	62	0.9287	0.1026	0.9287	0.9637
No log	6.4	64	0.9887	0.1026	0.9887	0.9943
No log	6.6	66	1.0648	0.1026	1.0648	1.0319
No log	6.8	68	1.1181	0.1642	1.1181	1.0574
No log	7.0	70	1.1241	0.1642	1.1241	1.0602
No log	7.2	72	1.0914	0.1026	1.0914	1.0447
No log	7.4	74	1.0636	0.1026	1.0636	1.0313
No log	7.6	76	1.0463	0.1026	1.0463	1.0229
No log	7.8	78	1.0315	0.1026	1.0315	1.0156
No log	8.0	80	1.0092	0.1026	1.0092	1.0046
No log	8.2	82	0.9865	0.1026	0.9865	0.9932
No log	8.4	84	0.9702	0.1026	0.9702	0.9850
No log	8.6	86	0.9677	0.1026	0.9677	0.9837
No log	8.8	88	0.9641	0.1026	0.9641	0.9819
No log	9.0	90	0.9647	0.1026	0.9647	0.9822
No log	9.2	92	0.9698	0.1026	0.9698	0.9848
No log	9.4	94	0.9691	0.1026	0.9691	0.9844
No log	9.6	96	0.9676	0.1026	0.9676	0.9837
No log	9.8	98	0.9670	0.1026	0.9670	0.9833
No log	10.0	100	0.9677	0.1026	0.9677	0.9837

Framework versions

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