This model is a fine-tuned version of microsoft/swinv2-tiny-patch4-window8-256 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.0482
Accuracy: 0.983

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: 450
eval_batch_size: 450
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 1800
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
0.3991	1.0	46	0.2074	0.933
0.1629	2.0	92	0.0946	0.971
0.1294	3.0	138	0.0692	0.977
0.1164	4.0	184	0.0572	0.982
0.1028	5.0	230	0.0494	0.984
0.0893	6.0	276	0.0487	0.982
0.0843	7.0	322	0.0472	0.984
0.0805	8.0	368	0.0437	0.983
0.0705	9.0	414	0.0523	0.982
0.0712	10.0	460	0.0482	0.983

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu121
Datasets 2.14.6
Tokenizers 0.14.1

Abhiram4/swinv2-tiny-patch4-window8-256-finetuned-eurosat

swinv2-tiny-patch4-window8-256-finetuned-eurosat

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Abhiram4/
swinv2-tiny-patch4-window8-256-finetuned-eurosat