This model is a fine-tuned version of google/vit-base-patch16-224 on the Multimodal-Fatima/OxfordFlowers_test_facebook_opt_1.3b_Visclues_ns_6149 dataset. It achieves the following results on the evaluation set:

Loss: 0.0540
Accuracy: 0.9951

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: 0.0003
train_batch_size: 16
eval_batch_size: 8
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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3164	1.0	308	0.1577	0.9919
0.0703	2.0	616	0.0557	0.9951
0.0416	3.0	924	0.0417	0.9967
0.0297	4.0	1232	0.0369	0.9967
0.0286	5.0	1540	0.0358	0.9967

Framework versions

Transformers 4.50.0
Pytorch 2.6.0+cu124
Datasets 3.4.1
Tokenizers 0.21.1

Zero-shot classification results

Accuracy: 0.7214 Precision: 0.7092 Recall: 0.7214

loretyan/vit-base-oxford-flowers-102

vit-base-oxford-flowers-102

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Zero-shot classification results

loretyan/
vit-base-oxford-flowers-102