The following hyperparameters were used during training:
learning_rate: 0.0002
train_batch_size: 2
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 40
num_epochs: 15
Training results
Framework versions
PEFT 0.12.0
Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.19.1
This project serves as an experimental step in building models aimed at preserving Arab-Islamic heritage using artificial intelligence.
The fine-tuning of the AraGPT2-large model on the text "Al-Tadmuriyah" by Shaykh al-Islam Ibn Taymiyyah represents the beginning of exploring how language models can enhance our understanding and appreciation of classical texts.
Insha'Allah, I will continue working on other projects in this domain to further contribute to this field
