ademola277/bert-base-uncased-finetuned-squad

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

• Train Loss: 0.0000
• Train End Logits Accuracy: 1.0
• Train Start Logits Accuracy: 1.0
• Validation Loss: 0.0011
• Validation End Logits Accuracy: 0.9995
• Validation Start Logits Accuracy: 1.0
• 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': '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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 13587, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
• training_precision: mixed_float16

Training results

Train Loss	Train End Logits Accuracy	Train Start Logits Accuracy	Validation Loss	Validation End Logits Accuracy	Validation Start Logits Accuracy	Epoch
0.0302	0.9944	0.9963	0.0024	0.9988	1.0	0
0.0002	0.9999	1.0000	0.0009	0.9998	1.0	1
0.0000	1.0	1.0	0.0011	0.9995	1.0	2

Framework versions

• Transformers 4.31.0
• TensorFlow 2.13.0
• Datasets 2.12.0
• Tokenizers 0.13.2