metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_keras_callback
model-index:
- name: CharlesBointon/item_classifier
results: []
CharlesBointon/item_classifier
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 1.8946
- Validation Loss: 1.9332
- Train Accuracy: 0.375
- 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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 480, '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 |
|---|---|---|---|
| 2.0880 | 2.0676 | 0.2083 | 0 |
| 2.0370 | 2.0331 | 0.25 | 1 |
| 1.9903 | 1.9986 | 0.2917 | 2 |
| 1.9406 | 1.9644 | 0.2917 | 3 |
| 1.8946 | 1.9332 | 0.375 | 4 |
Framework versions
- Transformers 4.32.0.dev0
- TensorFlow 2.9.1
- Datasets 2.14.2
- Tokenizers 0.12.1