arabert_baseline_vocabulary_task6_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: 0.4086
• Qwk: 0.7322
• Mse: 0.4086

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	0.5	2	1.1281	0.0558	1.1281
No log	1.0	4	0.6605	0.4309	0.6605
No log	1.5	6	0.8109	0.4615	0.8109
No log	2.0	8	0.8404	0.3450	0.8404
No log	2.5	10	0.7598	0.3277	0.7598
No log	3.0	12	0.4728	0.4717	0.4728
No log	3.5	14	0.4115	0.5238	0.4115
No log	4.0	16	0.4736	0.7219	0.4736
No log	4.5	18	0.4966	0.7135	0.4966
No log	5.0	20	0.4737	0.6595	0.4737
No log	5.5	22	0.4965	0.6595	0.4965
No log	6.0	24	0.4565	0.7068	0.4565
No log	6.5	26	0.5170	0.6595	0.5170
No log	7.0	28	0.4977	0.6595	0.4977
No log	7.5	30	0.4286	0.7322	0.4286
No log	8.0	32	0.3945	0.7778	0.3945
No log	8.5	34	0.3857	0.7778	0.3857
No log	9.0	36	0.3903	0.7778	0.3903
No log	9.5	38	0.4015	0.7778	0.4015
No log	10.0	40	0.4086	0.7322	0.4086

Framework versions

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