feizhe/vit-base-patch16-224-in21k-pheno-run4

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: 0.1288
• Train Accuracy: 1.0
• Train Top-3-accuracy: 1.0
• Validation Loss: 1.3621
• Validation Accuracy: 0.5789
• Validation Top-3-accuracy: 0.9123
• Epoch: 4

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: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 1938, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
• training_precision: mixed_float16

Training results

Train Loss	Train Accuracy	Train Top-3-accuracy	Validation Loss	Validation Accuracy	Validation Top-3-accuracy	Epoch
1.2677	0.6624	0.9206	1.3032	0.5088	0.9181	0
0.4847	0.9532	0.9990	1.2317	0.5556	0.9181	1
0.2287	0.9963	1.0	1.2755	0.5965	0.8947	2
0.1578	0.9991	1.0	1.3387	0.5731	0.9181	3
0.1288	1.0	1.0	1.3621	0.5789	0.9123	4

Framework versions

• Transformers 4.31.0
• TensorFlow 2.10.0
• Datasets 2.18.0
• Tokenizers 0.13.3