bert-base-practice

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

• Train Loss: 0.0039
• Train Accuracy: 0.9991
• Validation Loss: 0.1090
• Validation Accuracy: 0.9757
• Epoch: 4

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': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 5e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 2250, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 250, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.1}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Validation Loss	Validation Accuracy	Epoch
0.1662	0.9451	0.1118	0.9547	0
0.0730	0.9784	0.0894	0.9713	1
0.0381	0.9893	0.0781	0.9747	2
0.0142	0.9964	0.1005	0.9743	3
0.0039	0.9991	0.1090	0.9757	4

Framework versions

• Transformers 4.48.3
• TensorFlow 2.18.0
• Tokenizers 0.21.0