VIT_fourclass_Jun25

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: 0.0938
• Validation Loss: 2.3960
• Train Accuracy: 0.51
• Epoch: 14

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': 'SGD', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': np.float32(0.01), 'momentum': 0.0, 'nesterov': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Accuracy	Epoch
0.9196	1.2060	0.38	0
0.3792	1.4807	0.48	1
0.2729	1.7396	0.45	2
0.2006	2.4379	0.29	3
0.1996	2.4795	0.36	4
0.1734	2.7916	0.35	5
0.1860	4.1270	0.09	6
0.1490	2.7235	0.37	7
0.1077	3.5380	0.26	8
0.1173	2.7697	0.42	9
0.1526	2.7868	0.42	10
0.1161	3.1132	0.36	11
0.1093	3.5738	0.33	12
0.0884	3.1227	0.37	13
0.0938	2.3960	0.51	14

Framework versions

• Transformers 4.52.4
• TensorFlow 2.18.0
• Datasets 3.6.0
• Tokenizers 0.21.1