ArabicNewSplits_FineTuningAraBERT_noAug_task3_organization_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: 0.7850
• Qwk: 0.1623
• Mse: 0.7850
• Rmse: 0.8860

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: 8
• eval_batch_size: 8
• 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	Rmse
No log	2.0	2	3.1839	-0.0253	3.1839	1.7844
No log	4.0	4	1.7869	-0.0036	1.7869	1.3368
No log	6.0	6	0.7217	0.1795	0.7217	0.8495
No log	8.0	8	0.7222	0.1368	0.7222	0.8498
No log	10.0	10	0.7850	0.1623	0.7850	0.8860

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu118
• Datasets 2.21.0
• Tokenizers 0.19.1