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: 0.6839080459770115

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: 1.1036
Accuracy: 0.6839

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: 25
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.1638	1.1	100	1.0564	0.5471
0.8524	2.2	200	0.9403	0.6118
0.8231	3.3	300	0.8282	0.7176
0.7398	4.4	400	0.9056	0.6294
0.41	5.49	500	0.8815	0.6235
0.4849	6.59	600	0.9505	0.6294
0.3894	7.69	700	0.8052	0.6882
0.4678	8.79	800	0.8424	0.7059
0.4279	9.89	900	0.9639	0.6706
0.3461	10.99	1000	0.8497	0.7059
0.2741	12.09	1100	0.9090	0.7
0.1771	13.19	1200	0.8292	0.7118
0.1779	14.29	1300	1.1314	0.6294
0.2044	15.38	1400	0.8349	0.7294
0.1543	16.48	1500	0.8952	0.6941
0.1283	17.58	1600	0.8054	0.7353
0.1721	18.68	1700	0.9094	0.7235
0.1509	19.78	1800	0.9168	0.7412
0.1257	20.88	1900	0.9395	0.7412
0.1747	21.98	2000	0.8746	0.7471
0.1506	23.08	2100	0.7992	0.7353
0.1021	24.18	2200	0.7446	0.7706

Framework versions

Transformers 4.21.1
Pytorch 1.12.0+cu113
Datasets 2.4.0
Tokenizers 0.12.1