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

Loss: 1.0819
Accuracy: 0.65

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: 5e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 32

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.8696	5	2.1918	0.1125
2.1428	1.9130	11	2.1017	0.1625
2.1428	2.9565	17	1.9293	0.1875
1.8582	4.0	23	1.7163	0.325
1.8582	4.8696	28	1.5777	0.375
1.4818	5.9130	34	1.4303	0.45
1.1661	6.9565	40	1.3146	0.475
1.1661	8.0	46	1.2160	0.525
0.9421	8.8696	51	1.2096	0.55
0.9421	9.9130	57	1.1362	0.5875
0.8003	10.9565	63	1.1598	0.525
0.8003	12.0	69	1.0878	0.6
0.678	12.8696	74	1.0940	0.6375
0.5888	13.9130	80	1.0819	0.65
0.5888	14.9565	86	1.0700	0.625
0.5086	16.0	92	1.0758	0.625
0.5086	16.8696	97	1.0804	0.625
0.4454	17.9130	103	1.0704	0.6
0.4454	18.9565	109	1.1111	0.575
0.3758	20.0	115	1.0619	0.5875
0.3402	20.8696	120	1.0846	0.6125
0.3402	21.9130	126	1.1042	0.6125
0.3247	22.9565	132	1.0926	0.6375
0.3247	24.0	138	1.0908	0.625
0.3142	24.8696	143	1.0964	0.6
0.3142	25.9130	149	1.0999	0.6125
0.3081	26.9565	155	1.1036	0.625
0.276	27.8261	160	1.1019	0.625

Framework versions

Transformers 4.44.2
Pytorch 2.5.0+cu121
Datasets 3.0.2
Tokenizers 0.19.1

ntnxx2/vit-base-patch16-224-finetuned-Visual-Emotional

vit-base-patch16-224-finetuned-Visual-Emotional

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

ntnxx2/
vit-base-patch16-224-finetuned-Visual-Emotional