Rashed-vit-model

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.0047
• Accuracy: 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: 0.0002
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2279	1.9048	200	0.4485	0.9111
0.1335	3.8095	400	0.0680	0.9889
0.0061	5.7143	600	0.0047	1.0
0.0025	7.6190	800	0.0606	0.9778
0.0624	9.5238	1000	0.2500	0.9556
0.0013	11.4286	1200	0.0868	0.9889
0.001	13.3333	1400	0.0908	0.9889
0.0008	15.2381	1600	0.0935	0.9889
0.0006	17.1429	1800	0.0960	0.9889
0.0005	19.0476	2000	0.0979	0.9889
0.0004	20.9524	2200	0.0996	0.9889
0.0004	22.8571	2400	0.1013	0.9889
0.0003	24.7619	2600	0.1027	0.9889
0.0003	26.6667	2800	0.1040	0.9889
0.0003	28.5714	3000	0.1054	0.9889
0.0002	30.4762	3200	0.1065	0.9889
0.0002	32.3810	3400	0.1076	0.9889
0.0002	34.2857	3600	0.1085	0.9889
0.0002	36.1905	3800	0.1094	0.9889
0.0002	38.0952	4000	0.1102	0.9889
0.0002	40.0	4200	0.1109	0.9889
0.0001	41.9048	4400	0.1115	0.9889
0.0001	43.8095	4600	0.1120	0.9889
0.0001	45.7143	4800	0.1124	0.9889
0.0001	47.6190	5000	0.1126	0.9889
0.0001	49.5238	5200	0.1128	0.9889

Framework versions

• Transformers 4.43.3
• Pytorch 2.4.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1