<!-- 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. -->
frncscp/patacoptimus-prime
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on frncscp/patacon-730. It achieves the following results on the evaluation set:
- Train Loss: 0.0043
- Validation Loss: 0.0086
- Train Accuracy: 0.9977
- Epoch: 14
Model description
One-Class Patacognition Transformer
Intended uses & limitations
It was designed for One-Class Patacón Classification
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 34960, '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, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|---|---|---|---|
| 0.0064 | 0.0079 | 0.9977 | 0 |
| 0.0043 | 0.0086 | 0.9977 | 1 |
Framework versions
- Transformers 4.28.1
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
