arabert_baseline_style_task8_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: 0.3875
• Qwk: 0.7083
• Mse: 0.3875

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	1.0660	0.2857	1.0660
No log	1.0	4	0.9800	0.4940	0.9800
No log	1.5	6	0.5715	0.5758	0.5715
No log	2.0	8	0.9494	0.3957	0.9494
No log	2.5	10	0.4859	0.6111	0.4859
No log	3.0	12	0.3914	0.8048	0.3914
No log	3.5	14	0.4214	0.7388	0.4214
No log	4.0	16	0.4551	0.7388	0.4551
No log	4.5	18	0.5826	0.7083	0.5826
No log	5.0	20	0.5851	0.6392	0.5851
No log	5.5	22	0.5408	0.7083	0.5408
No log	6.0	24	0.4212	0.7298	0.4212
No log	6.5	26	0.3887	0.8205	0.3887
No log	7.0	28	0.3697	0.8048	0.3697
No log	7.5	30	0.3635	0.8048	0.3635
No log	8.0	32	0.3627	0.8048	0.3627
No log	8.5	34	0.3751	0.7159	0.3751
No log	9.0	36	0.3889	0.7083	0.3889
No log	9.5	38	0.3890	0.7083	0.3890
No log	10.0	40	0.3875	0.7083	0.3875

Framework versions

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