yuus2733/toyotacars_classifier

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: 0.3304
• Validation Loss: 1.1095
• Train Accuracy: 0.7028
• Epoch: 29

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': 43110, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': np.float32(0.9), 'beta_2': np.float32(0.999), 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Accuracy	Epoch
2.9793	2.8834	0.1556	0
2.8141	2.7550	0.25	1
2.6444	2.5301	0.3361	2
2.4691	2.3374	0.4722	3
2.2959	2.1452	0.5333	4
2.0945	2.0539	0.5389	5
1.9633	1.8626	0.5722	6
1.8124	1.8536	0.55	7
1.6898	1.6423	0.6083	8
1.5422	1.5292	0.6222	9
1.4272	1.4585	0.6306	10
1.3109	1.4785	0.6222	11
1.1907	1.3007	0.6861	12
1.0850	1.2980	0.6833	13
1.0577	1.2130	0.7056	14
0.9468	1.1251	0.7167	15
0.8517	1.3172	0.6472	16
0.8206	1.1645	0.7083	17
0.7459	1.1768	0.6972	18
0.6864	1.1457	0.6778	19
0.6379	1.1162	0.6972	20
0.5928	1.0945	0.7056	21
0.5569	1.0542	0.7139	22
0.5276	1.1110	0.7083	23
0.4715	1.0347	0.7222	24
0.4470	0.9403	0.7222	25
0.4112	0.9729	0.7222	26
0.4101	1.0422	0.6944	27
0.3707	1.0415	0.6917	28
0.3304	1.1095	0.7028	29

Framework versions

• Transformers 4.50.3
• TensorFlow 2.19.0
• Datasets 3.5.0
• Tokenizers 0.21.1