_finetunned_NougatArabic_AHR_jawi

This model is a fine-tuned version of MohamedRashad/arabic-base-nougat on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2242

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 6
• total_train_batch_size: 48
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss
0.309	0.9969	159	0.3013
0.2567	1.9958	318	0.2445
0.2003	2.9948	477	0.2294
0.1586	3.9937	636	0.2145
0.1149	4.9927	795	0.2172
0.1199	5.9979	955	0.2154
0.0957	6.9969	1114	0.2242

Framework versions

• Transformers 4.46.3
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.20.3