TirathP/vit-base-patch16-224-finetuned-customData

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

• Train Loss: 0.2775
• Validation Loss: 0.3297
• Validation Accuracy: 0.8571
• 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': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Validation Loss	Validation Accuracy	Epoch
1.1397	1.0223	0.5714	0
0.8312	0.8338	0.5714	1
0.7131	0.7099	0.5714	2
0.5754	0.6120	0.7143	3
0.4804	0.5374	0.7143	4
0.3934	0.4630	0.8571	5
0.4258	0.3979	0.8571	6
0.3739	0.3455	1.0	7
0.3143	0.2909	1.0	8
0.3113	0.2572	0.8571	9
0.3327	0.2623	0.8571	10
0.2227	0.2993	0.8571	11
0.2860	0.3299	0.8571	12
0.2081	0.3553	0.8571	13
0.2243	0.3360	0.8571	14
0.2246	0.2942	0.8571	15
0.2570	0.2131	0.8571	16
0.3173	0.1850	0.8571	17
0.1572	0.2134	0.8571	18
0.2775	0.3297	0.8571	19

Framework versions

• Transformers 4.31.0
• TensorFlow 2.12.0
• Datasets 2.14.4
• Tokenizers 0.13.3