README.md

metadata

tags:
  - generated_from_trainer
datasets:
  - image_folder
metrics:
  - f1
model-index:
  - name: vit_flyswot_test
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: image_folder
          type: image_folder
          args: default
        metrics:
          - name: F1
            type: f1
            value: 0.849172221610369

vit_flyswot_test

This model is a fine-tuned version of on the image_folder dataset. It achieves the following results on the evaluation set:

• Loss: 0.4777
• F1: 0.8492

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: 2e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 666
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	F1
No log	1.0	52	1.2007	0.3533
No log	2.0	104	1.0037	0.5525
No log	3.0	156	0.8301	0.6318
No log	4.0	208	0.7224	0.6946
No log	5.0	260	0.7298	0.7145
No log	6.0	312	0.6328	0.7729
No log	7.0	364	0.6010	0.7992
No log	8.0	416	0.5174	0.8364
No log	9.0	468	0.5084	0.8479
0.6372	10.0	520	0.4777	0.8492

Framework versions

• Transformers 4.17.0.dev0
• Pytorch 1.10.0+cu111
• Datasets 1.18.3
• Tokenizers 0.11.6