bert-base-nsmc

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: 0.0269
• Train Accuracy: 0.9923
• Validation Loss: 0.5523
• Validation Accuracy: 0.8722
• 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': 1058, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 117, '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
0.3945	0.8164	0.3522	0.8466	0
0.2128	0.9158	0.3317	0.8656	1
0.1030	0.9653	0.4110	0.8706	2
0.0465	0.9848	0.4870	0.8688	3
0.0269	0.9923	0.5523	0.8722	4

Framework versions

• Transformers 4.48.3
• TensorFlow 2.18.0
• Tokenizers 0.21.0