jangsukim/bert-base-nsmc

<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->

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: 0.0245
• —Train Accuracy: 0.9933
• —Validation Loss: 0.5325
• —Validation Accuracy: 0.8758
• —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', 'learningrate': {'module': 'transformers.optimizationtf', 'classname': 'WarmUp', 'config': {'initiallearningrate': 5e-05, 'decayschedulefn': {'module': 'keras.optimizers.schedules', 'classname': 'PolynomialDecay', 'config': {'initiallearningrate': 5e-05, 'decaysteps': 1058, 'endlearningrate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registeredname': None}, 'warmupsteps': 117, 'power': 1.0, 'name': None}, 'registeredname': 'WarmUp'}, 'decay': 0.0, 'beta1': np.float32(0.9), 'beta2': np.float32(0.999), 'epsilon': 1e-08, 'amsgrad': False, 'weightdecayrate': 0.1}
• —training_precision: float32

Training results

Framework versions

• —Transformers 4.51.1
• —TensorFlow 2.18.0
• —Tokenizers 0.21.1