arabert_baseline_style_task4_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: 0.2941
• Qwk: 0.4545
• Mse: 0.2941

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	3.5794	0.0	3.5794
No log	2.0	4	2.3016	0.0	2.3016
No log	3.0	6	1.5677	-0.0769	1.5677
No log	4.0	8	0.9593	0.0	0.9593
No log	5.0	10	0.4937	0.0	0.4937
No log	6.0	12	0.3911	-0.375	0.3911
No log	7.0	14	0.3754	0.0	0.3754
No log	8.0	16	0.3336	0.0588	0.3336
No log	9.0	18	0.3020	0.4545	0.3020
No log	10.0	20	0.2941	0.4545	0.2941

Framework versions

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