metadata
license: apache-2.0
base_model: moreover18/vit-base-patch16-224-in21k-finetuned-eurosat
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit-base-patch16-224-in21k-finetuned-eurosat-finetuned2
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: 0.9251711510905907
vit-base-patch16-224-in21k-finetuned-eurosat-finetuned2
This model is a fine-tuned version of moreover18/vit-base-patch16-224-in21k-finetuned-eurosat on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1871
- Accuracy: 0.9252
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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 |
|---|---|---|---|---|
| 0.2258 | 0.25 | 100 | 0.2074 | 0.9155 |
| 0.2291 | 0.51 | 200 | 0.2039 | 0.9132 |
| 0.212 | 0.76 | 300 | 0.1969 | 0.9147 |
| 0.2126 | 1.02 | 400 | 0.2026 | 0.9163 |
| 0.1822 | 1.27 | 500 | 0.1952 | 0.9175 |
| 0.1716 | 1.53 | 600 | 0.1892 | 0.9225 |
| 0.1847 | 1.78 | 700 | 0.1823 | 0.9261 |
| 0.1693 | 2.04 | 800 | 0.1879 | 0.9239 |
| 0.1438 | 2.29 | 900 | 0.1962 | 0.9206 |
| 0.1431 | 2.55 | 1000 | 0.1868 | 0.9261 |
| 0.1419 | 2.8 | 1100 | 0.1871 | 0.9252 |
Framework versions
- Transformers 4.35.2
- Pytorch 1.12.1+cu116
- Datasets 2.4.0
- Tokenizers 0.15.0