ArabicNewSplits5_FineTuningAraBERT_run2_AugV5_k1_task3_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: 0.7835
• Qwk: 0.1931
• Mse: 0.7835
• Rmse: 0.8851

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	5.5159	-0.0093	5.5159	2.3486
No log	0.4444	4	3.0274	0.0070	3.0274	1.7399
No log	0.6667	6	1.8881	-0.0246	1.8881	1.3741
No log	0.8889	8	2.7964	0.0494	2.7964	1.6722
No log	1.1111	10	2.4715	0.0484	2.4715	1.5721
No log	1.3333	12	1.2225	-0.0268	1.2225	1.1057
No log	1.5556	14	0.7943	-0.0370	0.7943	0.8912
No log	1.7778	16	0.7623	-0.1073	0.7623	0.8731
No log	2.0	18	0.7512	-0.0222	0.7512	0.8667
No log	2.2222	20	0.8023	0.0833	0.8023	0.8957
No log	2.4444	22	0.8851	0.1549	0.8851	0.9408
No log	2.6667	24	0.8197	-0.0370	0.8197	0.9054
No log	2.8889	26	0.7130	0.0400	0.7130	0.8444
No log	3.1111	28	0.7261	0.0725	0.7261	0.8521
No log	3.3333	30	0.6742	0.0725	0.6742	0.8211
No log	3.5556	32	0.8375	0.2217	0.8375	0.9152
No log	3.7778	34	1.3750	0.0241	1.3750	1.1726
No log	4.0	36	1.3756	0.0241	1.3756	1.1729
No log	4.2222	38	0.9945	0.1686	0.9945	0.9973
No log	4.4444	40	0.6866	0.2381	0.6866	0.8286
No log	4.6667	42	0.6553	0.0400	0.6553	0.8095
No log	4.8889	44	0.6525	0.1258	0.6525	0.8078
No log	5.1111	46	0.6578	0.1392	0.6578	0.8110
No log	5.3333	48	0.7186	0.2842	0.7186	0.8477
No log	5.5556	50	0.8407	0.2775	0.8407	0.9169
No log	5.7778	52	0.7791	0.2871	0.7791	0.8827
No log	6.0	54	0.7811	0.2762	0.7811	0.8838
No log	6.2222	56	0.7362	0.2919	0.7362	0.8580
No log	6.4444	58	0.7116	0.2239	0.7116	0.8436
No log	6.6667	60	0.7363	0.3271	0.7363	0.8581
No log	6.8889	62	0.7460	0.3301	0.7460	0.8637
No log	7.1111	64	0.7163	0.3116	0.7163	0.8463
No log	7.3333	66	0.7711	0.1527	0.7711	0.8781
No log	7.5556	68	0.7587	0.1456	0.7587	0.8711
No log	7.7778	70	0.7416	0.3116	0.7416	0.8612
No log	8.0	72	0.8078	0.2607	0.8078	0.8988
No log	8.2222	74	0.7970	0.3052	0.7970	0.8928
No log	8.4444	76	0.7583	0.3524	0.7583	0.8708
No log	8.6667	78	0.7520	0.3514	0.7520	0.8672
No log	8.8889	80	0.7880	0.1931	0.7880	0.8877
No log	9.1111	82	0.8449	0.2063	0.8449	0.9192
No log	9.3333	84	0.8511	0.2063	0.8511	0.9225
No log	9.5556	86	0.8214	0.2320	0.8214	0.9063
No log	9.7778	88	0.7945	0.2269	0.7945	0.8914
No log	10.0	90	0.7835	0.1931	0.7835	0.8851

Framework versions

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