README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - mnist
metrics:
  - accuracy
model-index:
  - name: image-classification
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: mnist
          type: mnist
          args: mnist
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9833333333333333
      - task:
          type: image-classification
          name: Image Classification
        dataset:
          name: autoevaluate/mnist-sample
          type: autoevaluate/mnist-sample
          config: autoevaluate--mnist-sample
          split: test
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.95
            verified: true
          - name: Precision Macro
            type: precision
            value: 0.9478535353535353
            verified: true
          - name: Precision Micro
            type: precision
            value: 0.95
            verified: true
          - name: Precision Weighted
            type: precision
            value: 0.9510353535353535
            verified: true
          - name: Recall Macro
            type: recall
            value: 0.9530555555555555
            verified: true
          - name: Recall Micro
            type: recall
            value: 0.95
            verified: true
          - name: Recall Weighted
            type: recall
            value: 0.95
            verified: true
          - name: F1 Macro
            type: f1
            value: 0.9496669557378175
            verified: true
          - name: F1 Micro
            type: f1
            value: 0.9500000000000001
            verified: true
          - name: F1 Weighted
            type: f1
            value: 0.9496869212452598
            verified: true
          - name: loss
            type: loss
            value: 0.12397973984479904
            verified: true
          - name: matthews_correlation
            type: matthews_correlation
            value: 0.9442456228021371
            verified: true

image-classification

This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the mnist dataset. It achieves the following results on the evaluation set:

• Loss: 0.0556
• Accuracy: 0.9833

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: 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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3743	1.0	422	0.0556	0.9833

Framework versions

• Transformers 4.20.0
• Pytorch 1.11.0+cu113
• Datasets 2.3.2
• Tokenizers 0.12.1