arabert_baseline_organization_task2_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: 0.4765
• Qwk: 0.5051
• Mse: 0.4812

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	3.4785	0.0139	3.4271
No log	0.6667	4	1.3527	0.0988	1.3438
No log	1.0	6	0.9762	0.0466	0.9710
No log	1.3333	8	0.5845	0.3068	0.5906
No log	1.6667	10	0.6355	0.4901	0.6479
No log	2.0	12	0.6002	0.4901	0.6080
No log	2.3333	14	0.5521	0.3591	0.5519
No log	2.6667	16	0.5671	0.5312	0.5733
No log	3.0	18	0.5298	0.5351	0.5340
No log	3.3333	20	0.5071	0.3871	0.4996
No log	3.6667	22	0.4892	0.3871	0.4817
No log	4.0	24	0.4557	0.5051	0.4597
No log	4.3333	26	0.5421	0.5205	0.5533
No log	4.6667	28	0.5017	0.5263	0.5115
No log	5.0	30	0.4329	0.5365	0.4364
No log	5.3333	32	0.4203	0.4431	0.4190
No log	5.6667	34	0.4083	0.4848	0.4015
No log	6.0	36	0.4520	0.4167	0.4366
No log	6.3333	38	0.4291	0.4396	0.4158
No log	6.6667	40	0.4230	0.4324	0.4110
No log	7.0	42	0.4029	0.4848	0.3965
No log	7.3333	44	0.4095	0.4848	0.4043
No log	7.6667	46	0.4194	0.4149	0.4149
No log	8.0	48	0.4324	0.5051	0.4317
No log	8.3333	50	0.4591	0.5051	0.4628
No log	8.6667	52	0.4758	0.4652	0.4811
No log	9.0	54	0.4791	0.4652	0.4844
No log	9.3333	56	0.4781	0.4652	0.4831
No log	9.6667	58	0.4760	0.5051	0.4806
No log	10.0	60	0.4765	0.5051	0.4812

Framework versions

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