Abhiram4's picture
Model save
da2af5a
metadata
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: vit-base-patch16-224-finetuned-eurosat
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.972

vit-base-patch16-224-finetuned-eurosat

This model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1017
  • Accuracy: 0.972

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
0.3243 1.0 46 0.2033 0.944
0.1247 2.0 92 0.0791 0.976
0.0937 3.0 138 0.0971 0.963
0.0716 4.0 184 0.0778 0.972
0.0543 5.0 230 0.0654 0.98
0.0367 6.0 276 0.0913 0.972
0.0292 7.0 322 0.0778 0.979
0.0204 8.0 368 0.0914 0.971
0.0161 9.0 414 0.1026 0.971
0.0154 10.0 460 0.1017 0.972

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.1.0+cu121
  • Datasets 2.14.6
  • Tokenizers 0.14.1