arabert_baseline_style_task3_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: 0.0331
• Qwk: 0.0
• Mse: 0.0316

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	0.6667	2	3.4993	0.0	3.4859
No log	1.3333	4	1.1380	0.0	1.1373
No log	2.0	6	0.1780	0.0	0.1784
No log	2.6667	8	0.0394	0.0	0.0397
No log	3.3333	10	0.0329	0.0	0.0323
No log	4.0	12	0.0230	0.0	0.0227
No log	4.6667	14	0.0116	0.0	0.0115
No log	5.3333	16	0.0132	0.0	0.0129
No log	6.0	18	0.0222	0.0	0.0217
No log	6.6667	20	0.0153	0.0	0.0148
No log	7.3333	22	0.0179	0.0	0.0172
No log	8.0	24	0.0268	0.0	0.0258
No log	8.6667	26	0.0322	0.0	0.0308
No log	9.3333	28	0.0335	0.0	0.0320
No log	10.0	30	0.0331	0.0	0.0316

Framework versions

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