Vit Base Patch16 384 Wi4

🚀 Imene/vit-base-patch16-384-wi4

This model is a fine - tuned version of google/vit-base-patch16-384 on an unknown dataset. It offers evaluation results that provide insights into its performance, such as train loss, accuracy, and validation metrics.

🚀 Quick Start

This model is a fine - tuned version of google/vit-base-patch16-384 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.1742
• Train Accuracy: 0.9982
• Train Top - 3 - accuracy: 0.9997
• Validation Loss: 1.5010
• Validation Accuracy: 0.5746
• Validation Top - 3 - accuracy: 0.8040
• Epoch: 10

📚 Documentation

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

🔧 Technical Details

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e - 05, 'decay_steps': 1800, '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}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
• training_precision: mixed_float16

Training results

Framework versions

• Transformers 4.21.3
• TensorFlow 2.8.2
• Datasets 2.4.0
• Tokenizers 0.12.1

📄 License

This model is licensed under the Apache 2.0 license.