_Nougat_base_Edv_Ar_Jw_03

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: 844.7745

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: 10
• total_train_batch_size: 80
• 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss
22.2135	1.0	51	10.0034
564.4659	2.0	102	133.0128
2128.3127	3.0	153	298.7846
3334.1366	4.0	204	430.0555
4976.2937	5.0	255	613.7381
6523.0763	6.0	306	735.7823
7514.8469	7.0	357	804.3959
7988.595	8.0	408	834.3971
8269.31	9.0	459	843.9667
8343.8331	9.8135	500	844.7745

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Tokenizers 0.21.0