metadata

license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_keras_callback
model-index:
  - name: arieg/bw_spec_cls_4_01_s_200
    results: []

arieg/bw_spec_cls_4_01_s_200

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: 0.0157
Train Sparse Categorical Accuracy: 1.0
Validation Loss: 0.0151
Validation Sparse Categorical Accuracy: 1.0
Epoch: 19

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', 'clipnorm': 1.0, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 14400, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_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	Train Sparse Categorical Accuracy	Validation Loss	Validation Sparse Categorical Accuracy	Epoch
0.7760	0.8944	0.3046	1.0	0
0.2006	1.0	0.1346	1.0	1
0.1136	1.0	0.0957	1.0	2
0.0865	1.0	0.0768	1.0	3
0.0712	1.0	0.0652	1.0	4
0.0611	1.0	0.0565	1.0	5
0.0532	1.0	0.0498	1.0	6
0.0471	1.0	0.0441	1.0	7
0.0420	1.0	0.0395	1.0	8
0.0376	1.0	0.0355	1.0	9
0.0339	1.0	0.0321	1.0	10
0.0307	1.0	0.0291	1.0	11
0.0279	1.0	0.0266	1.0	12
0.0255	1.0	0.0243	1.0	13
0.0233	1.0	0.0223	1.0	14
0.0214	1.0	0.0205	1.0	15
0.0198	1.0	0.0190	1.0	16
0.0183	1.0	0.0175	1.0	17
0.0169	1.0	0.0163	1.0	18
0.0157	1.0	0.0151	1.0	19

Framework versions

Transformers 4.35.0
TensorFlow 2.14.0
Datasets 2.14.6
Tokenizers 0.14.1