qnAr

This model is a fine-tuned version of ZeyadAhmed/AraElectra-Arabic-SQuADv2-QA on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.9324

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
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
1.8797	1.0	1208	1.8843
1.7562	2.0	2417	1.8879
1.6659	3.0	3624	1.9324

Framework versions

• Transformers 4.30.0
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.13.3