aditnnda/felidae_klasifikasi

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an Felidae Dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.5782
• Train Accuracy: 0.8361
• Validation Loss: 0.5283
• Validation Accuracy: 0.8361
• 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', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 3640, '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	Validation Loss	Validation Accuracy	Epoch
1.5945	0.5574	1.5482	0.5574	0
1.5213	0.7541	1.4625	0.7541	1
1.4429	0.7049	1.3574	0.7049	2
1.3399	0.7869	1.2390	0.7869	3
1.2264	0.6721	1.1328	0.6721	4
1.1660	0.7869	1.0287	0.7869	5
1.0825	0.7377	0.9690	0.7377	6
1.0005	0.8197	0.8654	0.8197	7
0.9121	0.7869	0.8303	0.7869	8
0.8530	0.8525	0.7590	0.8525	9
0.8602	0.8361	0.7169	0.8361	10
0.8420	0.8197	0.6993	0.8197	11
0.7772	0.8689	0.6347	0.8689	12
0.7447	0.8689	0.6023	0.8689	13
0.7253	0.8197	0.6458	0.8197	14
0.6994	0.8361	0.6045	0.8361	15
0.6761	0.8361	0.6030	0.8361	16
0.5814	0.8197	0.5523	0.8197	17
0.5939	0.8689	0.5456	0.8689	18
0.5782	0.8361	0.5283	0.8361	19

Framework versions

• Transformers 4.35.1
• TensorFlow 2.14.0
• Datasets 2.14.6
• Tokenizers 0.14.1