This model is a fine-tuned version of google/vit-base-patch16-224 on the bentrevett/caltech-ucsd-birds-200-2011 dataset. It achieves the following results on the evaluation set:

Loss: 1.0943
Accuracy: 0.7608

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: 16
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
5.0059	1.0	590	4.7309	0.1094
3.5528	2.0	1180	3.2157	0.5199
2.3284	3.0	1770	2.2254	0.6455
1.7561	4.0	2360	1.7277	0.6819
1.5242	5.0	2950	1.5194	0.6955
1.2769	6.0	3540	1.3285	0.7396
1.1813	7.0	4130	1.3044	0.7193
1.097	8.0	4720	1.1878	0.7506
1.1306	9.0	5310	1.1145	0.7566
0.9988	10.0	5900	1.0868	0.7506
0.9887	11.0	6490	1.0760	0.7659
0.9826	12.0	7080	1.0849	0.7634
0.9612	13.0	7670	1.0659	0.7642
0.9679	14.0	8260	1.0939	0.7455
1.0242	15.0	8850	1.0941	0.7472

Framework versions

Transformers 4.52.4
Pytorch 2.7.0
Datasets 3.6.0
Tokenizers 0.21.1

Marc-Hagenbusch/vit-base-caltech-ucsd-birds-200-2011

vit-base-caltech-ucsd-birds-200-2011

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Marc-Hagenbusch/
vit-base-caltech-ucsd-birds-200-2011