arabert_baseline_development_task7_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: 0.4808
• Qwk: 0.6800
• Mse: 0.4658

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	1.1708	0.1401	1.1442
No log	0.6667	4	0.6797	0.4733	0.6689
No log	1.0	6	0.8726	0.35	0.8601
No log	1.3333	8	0.6330	0.4407	0.6258
No log	1.6667	10	0.4729	0.7317	0.4705
No log	2.0	12	0.4560	0.7727	0.4525
No log	2.3333	14	0.4835	0.5161	0.4748
No log	2.6667	16	0.6021	0.4361	0.5871
No log	3.0	18	0.5490	0.5036	0.5343
No log	3.3333	20	0.4924	0.5772	0.4790
No log	3.6667	22	0.4506	0.6531	0.4384
No log	4.0	24	0.4816	0.6710	0.4656
No log	4.3333	26	0.5471	0.5818	0.5260
No log	4.6667	28	0.5883	0.4286	0.5652
No log	5.0	30	0.5645	0.4971	0.5423
No log	5.3333	32	0.4974	0.5823	0.4779
No log	5.6667	34	0.4623	0.6369	0.4450
No log	6.0	36	0.4534	0.6980	0.4376
No log	6.3333	38	0.4859	0.6369	0.4690
No log	6.6667	40	0.5046	0.5823	0.4879
No log	7.0	42	0.4998	0.6225	0.4840
No log	7.3333	44	0.4877	0.6434	0.4725
No log	7.6667	46	0.4853	0.6434	0.4702
No log	8.0	48	0.4746	0.6434	0.4601
No log	8.3333	50	0.4732	0.6434	0.4588
No log	8.6667	52	0.4819	0.6434	0.4671
No log	9.0	54	0.4873	0.6225	0.4722
No log	9.3333	56	0.4833	0.6800	0.4684
No log	9.6667	58	0.4812	0.6800	0.4662
No log	10.0	60	0.4808	0.6800	0.4658

Framework versions

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