malay-patel/bert-finetuned-squad-nq

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

• Train Loss: 1.5461
• Train End Logits Accuracy: 0.6253
• Train Start Logits Accuracy: 0.6120
• 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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 861, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, '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: mixed_float16

Training results

Train Loss	Train End Logits Accuracy	Train Start Logits Accuracy	Epoch
1.5548	0.6236	0.6172	0
1.5423	0.6286	0.6192	1
1.5461	0.6253	0.6120	2

Framework versions

• Transformers 4.24.0
• TensorFlow 2.9.2
• Datasets 2.7.1
• Tokenizers 0.13.2