arabert_baseline_organization_task5_fold0

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: 0.5797
• Qwk: 0.6737
• Mse: 0.5797

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: 16
• eval_batch_size: 16
• 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
No log	0.3333	2	1.3224	0.1029	1.3224
No log	0.6667	4	1.1724	0.0	1.1724
No log	1.0	6	1.0188	0.0	1.0188
No log	1.3333	8	0.9367	0.0	0.9367
No log	1.6667	10	0.9707	0.0461	0.9707
No log	2.0	12	1.0017	0.0940	1.0017
No log	2.3333	14	1.0101	0.3066	1.0101
No log	2.6667	16	0.9862	0.2453	0.9862
No log	3.0	18	0.9340	0.3962	0.9340
No log	3.3333	20	0.8741	0.4096	0.8741
No log	3.6667	22	0.8431	0.4403	0.8431
No log	4.0	24	0.7909	0.4898	0.7909
No log	4.3333	26	0.7355	0.5	0.7355
No log	4.6667	28	0.6751	0.6084	0.6751
No log	5.0	30	0.6350	0.5224	0.6350
No log	5.3333	32	0.6127	0.5224	0.6127
No log	5.6667	34	0.6032	0.5810	0.6032
No log	6.0	36	0.5973	0.5810	0.5973
No log	6.3333	38	0.5902	0.5810	0.5902
No log	6.6667	40	0.5956	0.7043	0.5956
No log	7.0	42	0.5976	0.7043	0.5976
No log	7.3333	44	0.5970	0.6401	0.5970
No log	7.6667	46	0.6061	0.6114	0.6061
No log	8.0	48	0.6064	0.6114	0.6064
No log	8.3333	50	0.5917	0.6401	0.5917
No log	8.6667	52	0.5644	0.6737	0.5644
No log	9.0	54	0.5637	0.6737	0.5637
No log	9.3333	56	0.5746	0.6737	0.5746
No log	9.6667	58	0.5782	0.6737	0.5782
No log	10.0	60	0.5797	0.6737	0.5797

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1