Ahmed-Zakaria/distilbert-base-cased-finetuned-squad

This model is a fine-tuned version of distilbert-base-cased-distilled-squad on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.3370
• Train End Logits Accuracy: 0.8992
• Train Start Logits Accuracy: 0.8669
• Validation Loss: 1.3575
• Validation End Logits Accuracy: 0.7082
• Validation Start Logits Accuracy: 0.6769
• Epoch: 2

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': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 16635, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Train End Logits Accuracy	Train Start Logits Accuracy	Validation Loss	Validation End Logits Accuracy	Validation Start Logits Accuracy	Epoch
0.6238	0.8207	0.7789	1.1257	0.7123	0.6807	0
0.4553	0.8655	0.8283	1.2318	0.7094	0.6784	1
0.3370	0.8992	0.8669	1.3575	0.7082	0.6769	2

Framework versions

• Transformers 4.36.0
• TensorFlow 2.13.0
• Datasets 2.1.0
• Tokenizers 0.15.0