vit_4090

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

• Loss: 0.0003
• Accuracy: 1.0
• Precision: 1.0
• Recall: 1.0
• F1: 1.0

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:

• learning_rate: 0.0001
• train_batch_size: 24
• eval_batch_size: 4
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.1909	1.0	865	0.0626	0.9840	0.9841	0.9840	0.9834
0.0747	2.0	1730	0.0403	0.9874	0.9876	0.9874	0.9869
0.0489	3.0	2595	0.0757	0.9788	0.9811	0.9788	0.9790
0.0352	4.0	3460	0.0187	0.9922	0.9924	0.9922	0.9923
0.0295	5.0	4325	0.0738	0.9792	0.9808	0.9792	0.9791
0.0248	6.0	5190	0.0196	0.9939	0.9940	0.9939	0.9939
0.0172	7.0	6055	0.0281	0.9939	0.9944	0.9939	0.9940
0.0205	8.0	6920	0.0052	0.9983	0.9983	0.9983	0.9983
0.0122	9.0	7785	0.0462	0.9883	0.9885	0.9883	0.9881
0.0106	10.0	8650	0.0258	0.9952	0.9953	0.9952	0.9952
0.0105	11.0	9515	0.0119	0.9974	0.9974	0.9974	0.9974
0.0073	12.0	10380	0.0081	0.9970	0.9970	0.9970	0.9970
0.0052	13.0	11245	0.0034	0.9991	0.9991	0.9991	0.9991
0.0031	14.0	12110	0.0169	0.9957	0.9957	0.9957	0.9956
0.0042	15.0	12975	0.0048	0.9991	0.9991	0.9991	0.9991
0.0014	16.0	13840	0.0015	0.9991	0.9991	0.9991	0.9991
0.0005	17.0	14705	0.0004	1.0	1.0	1.0	1.0
0.0001	18.0	15570	0.0026	0.9996	0.9996	0.9996	0.9996
0.0002	19.0	16435	0.0008	0.9996	0.9996	0.9996	0.9996
0.0002	20.0	17300	0.0003	1.0	1.0	1.0	1.0

Framework versions

• Transformers 4.49.0
• Pytorch 2.5.1
• Datasets 3.2.0
• Tokenizers 0.21.1