NougatArabic_CL_selfsupervised_DANN_GER

This model is a fine-tuned version of facebook/nougat-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0051

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: 10
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 6
• total_train_batch_size: 60
• 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: 15

Training results

Training Loss	Epoch	Step	Validation Loss
6.4887	1.0	82	0.7599
6.2319	2.0	164	1.1137
5.437	3.0	246	1.0468
4.9033	4.0	328	1.0051

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 4.0.0
• Tokenizers 0.21.0