arieg/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: 0.0156
• Validation Loss: 0.0151
• Train 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	Validation Loss	Train Accuracy	Epoch
0.7193	0.2997	1.0	0
0.2007	0.1391	1.0	1
0.1164	0.0981	1.0	2
0.0881	0.0788	1.0	3
0.0724	0.0664	1.0	4
0.0618	0.0573	1.0	5
0.0537	0.0502	1.0	6
0.0474	0.0445	1.0	7
0.0421	0.0397	1.0	8
0.0377	0.0357	1.0	9
0.0339	0.0322	1.0	10
0.0307	0.0292	1.0	11
0.0279	0.0266	1.0	12
0.0254	0.0243	1.0	13
0.0233	0.0223	1.0	14
0.0214	0.0205	1.0	15
0.0197	0.0189	1.0	16
0.0182	0.0175	1.0	17
0.0168	0.0162	1.0	18
0.0156	0.0151	1.0	19

Framework versions

• Transformers 4.35.0
• TensorFlow 2.14.0
• Datasets 2.14.6
• Tokenizers 0.14.1