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: 0.0275
• Train Accuracy: 0.9919
• Validation Loss: 0.5478
• Validation Accuracy: 0.8752
• 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': np.float32(0.9), 'beta_2': np.float32(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
0.4083	0.8070	0.3086	0.8676	0
0.2225	0.9093	0.3380	0.8758	1
0.1070	0.9619	0.4286	0.8654	2
0.0509	0.9827	0.4933	0.8736	3
0.0275	0.9919	0.5478	0.8752	4

Framework versions

• Transformers 4.57.6
• TensorFlow 2.19.0
• Datasets 4.0.0
• Tokenizers 0.22.2