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: 0.9868
Accuracy: 0.7451

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: 5.5e-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: 0.05
num_epochs: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.96	6	1.3771	0.3137
1.3705	1.92	12	1.3219	0.5490
1.3705	2.88	18	1.2517	0.5490
1.2535	4.0	25	1.1875	0.5882
1.1079	4.96	31	1.1237	0.6078
1.1079	5.92	37	1.1003	0.6275
1.0048	6.88	43	1.0609	0.6863
0.9172	8.0	50	1.0668	0.6078
0.9172	8.96	56	1.0031	0.6667
0.8558	9.92	62	0.9868	0.7451
0.8558	10.88	68	0.9763	0.7451
0.8284	11.52	72	0.9733	0.7451

Framework versions

Transformers 4.36.2
Pytorch 2.1.2+cu118
Datasets 2.16.1
Tokenizers 0.15.0

Augusto777/vit-base-patch16-224-ve-b-U10-12

vit-base-patch16-224-ve-b-U10-12

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Augusto777/
vit-base-patch16-224-ve-b-U10-12