arabert_baseline_vocabulary_task4_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: 1.1529
• Qwk: 0.1724
• Mse: 1.1529

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	1.0	2	3.1705	0.0704	3.1705
No log	2.0	4	1.2678	0.0123	1.2678
No log	3.0	6	0.6681	0.1111	0.6681
No log	4.0	8	0.7489	0.4839	0.7489
No log	5.0	10	0.9971	0.1724	0.9971
No log	6.0	12	1.2195	0.1724	1.2195
No log	7.0	14	1.2558	0.1724	1.2558
No log	8.0	16	1.1787	0.1724	1.1787
No log	9.0	18	1.1576	0.1724	1.1576
No log	10.0	20	1.1529	0.1724	1.1529

Framework versions

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