This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the bird_species_dataset dataset. It achieves the following results on the evaluation set:

Loss: 3.0432
Accuracy: 0.8051

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-06
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
5.7612	1.0	4232	5.6983	0.6094
5.2463	2.0	8464	5.1675	0.7284
4.718	3.0	12696	4.7034	0.7526
4.3011	4.0	16928	4.2762	0.7740
3.9042	5.0	21160	3.9123	0.7867
3.5981	6.0	25392	3.6050	0.7936
3.328	7.0	29624	3.3598	0.8015
3.164	8.0	33856	3.1819	0.8053
3.0241	9.0	38088	3.0878	0.8052
2.9784	10.0	42320	3.0420	0.8095

Framework versions

Transformers 4.38.1
Pytorch 2.1.2
Datasets 2.1.0
Tokenizers 0.15.2

gungbgs/bird_species_classifier

bird_species_classifier

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

gungbgs/
bird_species_classifier