README.md

metadata

base_model: microsoft/dit-large
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: MRR_image_classification_dit_29_jan_small75-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: 0.47560975609756095

MRR_image_classification_dit_29_jan_small75-finetuned-eurosat

This model is a fine-tuned version of microsoft/dit-large on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 1.5785
• Accuracy: 0.4756

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• 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
1.8795	0.98	10	1.6437	0.3049
1.6681	1.95	20	1.6446	0.4146
1.5603	2.93	30	1.5785	0.4756

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.1