Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
bert-base-nsmc – AI Model by swhong | AlphaNeural AI
You can deploy this model and start earning money today!
swhong
/
bert-base-nsmc
like
0
transformers
tf
safetensors
bert
text-classification
generated_from_keras_callback
klue/bert-base
finetune
cc-by-sa-4.0
autotrain_compatible
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
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: 0.0259
Train Accuracy: 0.9923
Validation Loss: 0.5580
Validation Accuracy: 0.8716
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
0.4051
0.8037
0.3180
0.8632
0
0.2253
0.9115
0.3153
0.8732
1
0.1065
0.9623
0.3866
0.8738
2
0.0505
0.9839
0.5163
0.8724
3
0.0259
0.9923
0.5580
0.8716
4
Framework versions
Transformers 4.50.3
TensorFlow 2.13.0
Tokenizers 0.21.1
