arabert_baseline_style_task3_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: 0.6911
• Qwk: 0.0
• Mse: 0.7019

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	3.4019	-0.0069	3.3417
No log	1.3333	4	1.2359	-0.1172	1.2020
No log	2.0	6	0.6141	0.0	0.5883
No log	2.6667	8	0.6682	-0.0476	0.6667
No log	3.3333	10	0.4760	0.0472	0.4717
No log	4.0	12	0.4843	-0.0784	0.4902
No log	4.6667	14	0.6953	-0.0476	0.7063
No log	5.3333	16	0.5093	-0.0476	0.5145
No log	6.0	18	0.3933	-0.1379	0.3915
No log	6.6667	20	0.4494	-0.0476	0.4514
No log	7.3333	22	0.5244	-0.0476	0.5293
No log	8.0	24	0.6106	0.0	0.6182
No log	8.6667	26	0.7248	0.0	0.7351
No log	9.3333	28	0.7173	0.0	0.7282
No log	10.0	30	0.6911	0.0	0.7019

Framework versions

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