metadata

license: apache-2.0
tags:
  - image-classification
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: croupier-creature-classifier
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: croupier-mtg-dataset
          type: imagefolder
          config: alkzar90--croupier-mtg-dataset
          split: train
          args: alkzar90--croupier-mtg-dataset
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8058823529411765

croupier-creature-classifier

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

Loss: 0.6480
Accuracy: 0.8059

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: 15
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1967	1.1	100	0.6480	0.8059
0.1047	2.2	200	0.8703	0.7529
0.2249	3.3	300	0.9539	0.7588
0.0984	4.4	400	0.9319	0.7529
0.086	5.49	500	0.9061	0.7706
0.1164	6.59	600	0.7493	0.8176
0.0518	7.69	700	0.8781	0.7765
0.0458	8.79	800	0.8851	0.7824
0.0521	9.89	900	0.9448	0.7882
0.0576	10.99	1000	0.8884	0.7824
0.0442	12.09	1100	0.8965	0.7882
0.0254	13.19	1200	0.9140	0.7882
0.0426	14.29	1300	0.9274	0.7882

Framework versions

Transformers 4.21.0
Pytorch 1.12.0+cu113
Datasets 2.4.0
Tokenizers 0.12.1