metadata
license: apache-2.0
base_model: facebook/vit-msn-small
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit-msn-small-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: 0.8105263157894737
vit-msn-small-finetuned-eurosat
This model is a fine-tuned version of facebook/vit-msn-small on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.6607
- Accuracy: 0.8105
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.115 | 0.9362 | 11 | 1.0397 | 0.6526 |
| 0.8536 | 1.9574 | 23 | 0.7698 | 0.7579 |
| 0.5677 | 2.9787 | 35 | 0.7200 | 0.7895 |
| 0.419 | 4.0 | 47 | 0.7286 | 0.7842 |
| 0.3365 | 4.9362 | 58 | 0.6607 | 0.8105 |
| 0.2317 | 5.6170 | 66 | 0.6649 | 0.8 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1