Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
Heresy-clustered – AI Model by recklessrecursion | AlphaNeural AI | AlphaNeural AI
You can deploy this model and start earning money today!
recklessrecursion
/
Heresy-clustered
like
0
transformers
tf
distilbert
question-answering
generated_from_keras_callback
mit
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
recklessrecursion/Heresy-clustered
This model is a fine-tuned version of
nandysoham16/11-clustered_aug
on an unknown dataset. It achieves the following results on the evaluation set:
Train Loss: 0.1793
Train End Logits Accuracy: 0.9618
Train Start Logits Accuracy: 0.9549
Validation Loss: 0.7725
Validation End Logits Accuracy: 0.6667
Validation Start Logits Accuracy: 0.3333
Epoch: 0
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': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 18, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
training_precision: float32
Training results
Train Loss
Train End Logits Accuracy
Train Start Logits Accuracy
Validation Loss
Validation End Logits Accuracy
Validation Start Logits Accuracy
Epoch
0.1793
0.9618
0.9549
0.7725
0.6667
0.3333
0
Framework versions
Transformers 4.26.0
TensorFlow 2.9.2
Datasets 2.9.0
Tokenizers 0.13.2
