teddythinh/distilbert-base-uncased-finetuned-squad

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

• Train Loss: 0.9755
• Train End Logits Accuracy: 0.7326
• Train Start Logits Accuracy: 0.6950
• Validation Loss: 1.2886
• Validation End Logits Accuracy: 0.6681
• Validation Start Logits Accuracy: 0.6373
• Epoch: 1

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': 5524, '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
1.6197	0.5830	0.5477	1.3354	0.6514	0.6252	0
0.9755	0.7326	0.6950	1.2886	0.6681	0.6373	1

Framework versions

• Transformers 4.35.2
• TensorFlow 2.15.0
• Datasets 2.16.1
• Tokenizers 0.15.0