This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the bird-data dataset. It achieves the following results on the evaluation set:

Loss: 0.6642
Accuracy: 0.8215

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: 0.0002
train_batch_size: 72
eval_batch_size: 72
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 288
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
3.8854	0.99	74	3.0164	0.3039
2.066	1.99	148	1.4849	0.6095
1.5066	2.99	222	1.0624	0.7145
1.1904	3.99	296	0.9347	0.7450
0.9986	4.99	370	0.8415	0.7709
0.9437	5.99	444	0.7713	0.7901
0.8297	6.99	518	0.7216	0.8081
0.7805	7.99	592	0.6856	0.8152
0.6978	8.99	666	0.6642	0.8215
0.6147	9.99	740	0.6525	0.8207

Framework versions

Transformers 4.26.1
Pytorch 1.13.1+cu116
Datasets 2.10.1
Tokenizers 0.13.2

gjuggler/swin-tiny-patch4-window7-224-finetuned-birds

swin-tiny-patch4-window7-224-finetuned-birds

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

gjuggler/
swin-tiny-patch4-window7-224-finetuned-birds