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: 0.6698
Accuracy: 0.8478

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: 24

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.97	7	1.3673	0.4783
1.3789	1.93	14	1.2760	0.5435
1.2878	2.9	21	1.1732	0.5435
1.2878	4.0	29	1.0471	0.5435
1.128	4.97	36	0.9960	0.5435
0.9873	5.93	43	0.8939	0.6304
0.8611	6.9	50	0.8650	0.6087
0.8611	8.0	58	0.8442	0.6304
0.7397	8.97	65	0.7331	0.7174
0.6326	9.93	72	0.6698	0.8478
0.6326	10.9	79	0.7430	0.7391
0.5424	12.0	87	0.7030	0.7609
0.4687	12.97	94	0.6352	0.8043
0.404	13.93	101	0.5498	0.8043
0.404	14.9	108	0.5631	0.8043
0.3244	16.0	116	0.5706	0.8261
0.305	16.97	123	0.6010	0.8043
0.2819	17.93	130	0.5845	0.7826
0.2819	18.9	137	0.5594	0.8043
0.2487	20.0	145	0.5567	0.8043
0.2297	20.97	152	0.5489	0.8043
0.2297	21.93	159	0.5556	0.7826
0.2177	22.9	166	0.5519	0.8043
0.2177	23.17	168	0.5515	0.8043

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-U14-b-24

vit-base-patch16-224-ve-U14-b-24

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Augusto777/
vit-base-patch16-224-ve-U14-b-24