ArabicNewSplits_FineTuningAraBERT_AugV5_k2_task2_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: 0.6878
• Qwk: 0.1223
• Mse: 0.6878
• Rmse: 0.8293

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	0.2222	2	2.5798	0.0054	2.5798	1.6062
No log	0.4444	4	1.7870	-0.0032	1.7870	1.3368
No log	0.6667	6	1.4008	0.1380	1.4008	1.1836
No log	0.8889	8	1.1615	0.0	1.1615	1.0777
No log	1.1111	10	1.0976	0.0	1.0976	1.0476
No log	1.3333	12	0.9974	0.0	0.9974	0.9987
No log	1.5556	14	0.8439	0.0	0.8439	0.9186
No log	1.7778	16	0.7419	0.0	0.7419	0.8614
No log	2.0	18	0.7203	0.0	0.7203	0.8487
No log	2.2222	20	0.7435	0.0	0.7435	0.8622
No log	2.4444	22	0.7657	0.0	0.7657	0.8751
No log	2.6667	24	0.7549	0.0	0.7549	0.8689
No log	2.8889	26	0.7606	0.0	0.7606	0.8721
No log	3.1111	28	0.7338	0.0	0.7338	0.8566
No log	3.3333	30	0.7064	0.0	0.7064	0.8405
No log	3.5556	32	0.6880	0.0	0.6880	0.8295
No log	3.7778	34	0.6824	0.0	0.6824	0.8261
No log	4.0	36	0.6828	0.1015	0.6828	0.8263
No log	4.2222	38	0.6970	0.1015	0.6970	0.8348
No log	4.4444	40	0.6805	0.1224	0.6805	0.8249
No log	4.6667	42	0.6680	0.2428	0.6680	0.8173
No log	4.8889	44	0.6707	0.3212	0.6707	0.8189
No log	5.1111	46	0.6734	0.3238	0.6734	0.8206
No log	5.3333	48	0.6625	0.3489	0.6625	0.8139
No log	5.5556	50	0.6548	0.3316	0.6548	0.8092
No log	5.7778	52	0.6411	0.2432	0.6411	0.8007
No log	6.0	54	0.6297	0.2211	0.6297	0.7935
No log	6.2222	56	0.6294	0.2162	0.6294	0.7934
No log	6.4444	58	0.6341	0.2191	0.6341	0.7963
No log	6.6667	60	0.6445	0.2573	0.6445	0.8028
No log	6.8889	62	0.6451	0.2220	0.6451	0.8032
No log	7.1111	64	0.6412	0.2028	0.6412	0.8008
No log	7.3333	66	0.6400	0.2028	0.6400	0.8000
No log	7.5556	68	0.6405	0.2162	0.6405	0.8003
No log	7.7778	70	0.6434	0.1776	0.6434	0.8021
No log	8.0	72	0.6478	0.1450	0.6478	0.8049
No log	8.2222	74	0.6534	0.1512	0.6534	0.8083
No log	8.4444	76	0.6593	0.0998	0.6593	0.8120
No log	8.6667	78	0.6658	0.1191	0.6658	0.8160
No log	8.8889	80	0.6722	0.1191	0.6722	0.8199
No log	9.1111	82	0.6761	0.1191	0.6761	0.8223
No log	9.3333	84	0.6808	0.1191	0.6808	0.8251
No log	9.5556	86	0.6842	0.1031	0.6842	0.8272
No log	9.7778	88	0.6868	0.1223	0.6868	0.8287
No log	10.0	90	0.6878	0.1223	0.6878	0.8293

Framework versions

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