img_class_beans / README.md
juniorjukeko's picture
juniorjukeko/img_class_beans
1f348fc
|
raw
history blame
2.34 kB
metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
datasets:
  - beans
metrics:
  - accuracy
model-index:
  - name: img_class_beans
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: beans
          type: beans
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9498069498069498

img_class_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: 0.1818
  • Accuracy: 0.9498

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: 16
  • eval_batch_size: 16
  • seed: 143
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • 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
1.0147 0.98 12 0.8254 0.8494
0.7452 1.96 24 0.4785 0.9266
0.452 2.94 36 0.3032 0.9344
0.2861 4.0 49 0.2146 0.9459
0.155 4.98 61 0.1719 0.9575
0.1318 5.96 73 0.1655 0.9730
0.1311 6.94 85 0.1550 0.9691
0.1163 8.0 98 0.1710 0.9459
0.1006 8.98 110 0.1752 0.9459
0.1045 9.8 120 0.1472 0.9614

Framework versions

  • Transformers 4.33.2
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3