EyesNewFiveclassTryAfterYolo-agument

This model is a fine-tuned version of google/vit-base-patch16-224 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0039
• Train Accuracy: 0.9688
• Train Top-3-accuracy: 1.0
• Validation Loss: 0.0779
• Validation Accuracy: 0.9688
• Validation Top-3-accuracy: 0.9961
• Epoch: 9

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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 1270, '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 Accuracy	Train Top-3-accuracy	Validation Loss	Validation Accuracy	Validation Top-3-accuracy	Epoch
0.5486	0.9492	0.9674	0.1847	0.9492	1.0	0
0.1032	0.9492	0.9980	0.1171	0.9492	0.9961	1
0.0359	0.9688	1.0	0.1081	0.9688	0.9961	2
0.0179	0.9688	1.0	0.0958	0.9688	0.9961	3
0.0121	0.9688	1.0	0.0749	0.9688	0.9961	4
0.0074	0.9688	1.0	0.0765	0.9688	0.9961	5
0.0066	0.9688	1.0	0.0812	0.9688	0.9961	6
0.0054	0.9688	1.0	0.0823	0.9688	0.9961	7
0.0046	0.9688	1.0	0.0777	0.9688	0.9961	8
0.0039	0.9688	1.0	0.0779	0.9688	0.9961	9

Framework versions

• Transformers 4.42.4
• TensorFlow 2.17.0
• Datasets 2.20.0
• Tokenizers 0.19.1