metadata
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swin-tiny-patch4-window7-224-finetuned-eurosat
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.5621859296482412
swin-tiny-patch4-window7-224-finetuned-eurosat
This model was trained from scratch on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.0586
- Accuracy: 0.5622
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: 128
- eval_batch_size: 128
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.2768 | 1.0 | 28 | 1.1502 | 0.5031 |
1.124 | 2.0 | 56 | 1.0781 | 0.5440 |
1.0833 | 3.0 | 84 | 1.0586 | 0.5622 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.2+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2