README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - beans
metrics:
  - accuracy
model-index:
  - name: vit_beans
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: beans
          type: beans
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9699248120300752
      - task:
          type: image-classification
          name: Image Classification
        dataset:
          name: beans
          type: beans
          config: default
          split: test
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9296875
            verified: true
          - name: Precision Macro
            type: precision
            value: 0.9320220841959972
            verified: true
          - name: Precision Micro
            type: precision
            value: 0.9296875
            verified: true
          - name: Precision Weighted
            type: precision
            value: 0.9314910067287785
            verified: true
          - name: Recall Macro
            type: recall
            value: 0.9298634182355112
            verified: true
          - name: Recall Micro
            type: recall
            value: 0.9296875
            verified: true
          - name: Recall Weighted
            type: recall
            value: 0.9296875
            verified: true
          - name: F1 Macro
            type: f1
            value: 0.9303585725877088
            verified: true
          - name: F1 Micro
            type: f1
            value: 0.9296875
            verified: true
          - name: F1 Weighted
            type: f1
            value: 0.930005047716538
            verified: true
          - name: loss
            type: loss
            value: 0.23633646965026855
            verified: true

vit_beans

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the beans dataset. It achieves the following results on the evaluation set:

• Loss: 0.1176
• Accuracy: 0.9699

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: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1

Training results

Framework versions

• Transformers 4.14.1
• Pytorch 1.10.2
• Datasets 2.0.0
• Tokenizers 0.10.3