Entrnal_5class_agumm_last_newV7_model

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: 0.0959
• Train Accuracy: 0.9365
• Train Top-3-accuracy: 0.9913
• Validation Loss: 0.3424
• Validation Accuracy: 0.9390
• Validation Top-3-accuracy: 0.9917
• 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': 620, '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
1.1895	0.4833	0.8342	0.8125	0.6525	0.9200	0
0.5511	0.7329	0.9448	0.4587	0.7829	0.9601	1
0.3174	0.8164	0.9677	0.3909	0.8395	0.9735	2
0.2299	0.8576	0.9772	0.3711	0.8709	0.9802	3
0.1699	0.8824	0.9824	0.3564	0.8920	0.9842	4
0.1344	0.9003	0.9856	0.3389	0.9073	0.9865	5
0.1187	0.9131	0.9875	0.3391	0.9183	0.9884	6
0.1060	0.9229	0.9891	0.3424	0.9267	0.9898	7
0.0992	0.9304	0.9903	0.3426	0.9334	0.9908	8
0.0959	0.9365	0.9913	0.3424	0.9390	0.9917	9

Framework versions

• Transformers 4.44.2
• TensorFlow 2.15.1
• Datasets 3.0.0
• Tokenizers 0.19.1