mdeberta_quran_qa_model

<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->

hemagamal/mdeberta_quran_qa_model

This model is a fine-tuned version of timpal0l/mdeberta-v3-base-squad2 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 11.9013
• Train End Logits Loss: 5.9506
• Train Start Logits Loss: 5.9506
• Train End Logits Sparse Categorical Accuracy: 0.0582
• Train Start Logits Sparse Categorical Accuracy: 0.0426
• Validation Loss: 11.9013
• Validation End Logits Loss: 5.9506
• Validation Start Logits Loss: 5.9506
• Validation End Logits Sparse Categorical Accuracy: 0.0459
• Validation Start Logits Sparse Categorical Accuracy: 0.0917
• Epoch: 15

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:

• optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 2e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: float32

Training results

Framework versions

• Transformers 4.29.1
• TensorFlow 2.12.0
• Datasets 2.12.0
• Tokenizers 0.13.3