README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - beans
metrics:
  - accuracy
model-index:
  - name: convnext-tiny-finetuned-beans
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: beans
          type: beans
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9609375
      - task:
          type: image-classification
          name: Image Classification
        dataset:
          name: beans
          type: beans
          config: default
          split: test
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9609375
            verified: true
          - name: Precision Macro
            type: precision
            value: 0.9652777777777778
            verified: true
          - name: Precision Micro
            type: precision
            value: 0.9609375
            verified: true
          - name: Precision Weighted
            type: precision
            value: 0.9650065104166667
            verified: true
          - name: Recall Macro
            type: recall
            value: 0.9608711701734958
            verified: true
          - name: Recall Micro
            type: recall
            value: 0.9609375
            verified: true
          - name: Recall Weighted
            type: recall
            value: 0.9609375
            verified: true
          - name: F1 Macro
            type: f1
            value: 0.9615067076130842
            verified: true
          - name: F1 Micro
            type: f1
            value: 0.9609375
            verified: true
          - name: F1 Weighted
            type: f1
            value: 0.9613965275467993
            verified: true
          - name: loss
            type: loss
            value: 0.14331591129302979
            verified: true

convnext-tiny-finetuned-beans

This model is a fine-tuned version of facebook/convnext-tiny-224 on the beans dataset. It achieves the following results on the evaluation set:

• Loss: 0.1255
• Accuracy: 0.9609

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: 7171
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	37	0.6175	0.8828
No log	2.0	74	0.2307	0.9609
0.5237	3.0	111	0.1406	0.9531
0.5237	4.0	148	0.1165	0.9688
0.5237	5.0	185	0.1255	0.9609

Framework versions

• Transformers 4.18.0
• Pytorch 1.10.0+cu111
• Datasets 2.1.0
• Tokenizers 0.12.1