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