Text Classification
Transformers
TensorFlow
bert
generated_from_keras_callback
text-embeddings-inference
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("Ohjunghyun/bert-base-nsmc")
model = AutoModelForSequenceClassification.from_pretrained("Ohjunghyun/bert-base-nsmc")Quick Links
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: 0.1942
- Train Accuracy: 0.9247
- Validation Loss: 0.3159
- Validation Accuracy: 0.8760
- Epoch: 1
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': 423, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 47, '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 |
|---|---|---|---|---|
| 0.3708 | 0.8309 | 0.3033 | 0.8726 | 0 |
| 0.1942 | 0.9247 | 0.3159 | 0.8760 | 1 |
Framework versions
- Transformers 4.51.3
- TensorFlow 2.18.0
- Tokenizers 0.21.1
- Downloads last month
- -
Model tree for Ohjunghyun/bert-base-nsmc
Base model
klue/bert-base
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Ohjunghyun/bert-base-nsmc")