metadata

library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: test_trainer
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.45

test_trainer

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

Loss: 1.7380
Accuracy: 0.45

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: 64
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	10	2.0828	0.1688
No log	2.0	20	2.0820	0.1688
No log	3.0	30	2.0807	0.175
No log	4.0	40	2.0789	0.1875
No log	5.0	50	2.0763	0.1938
No log	6.0	60	2.0733	0.1875
No log	7.0	70	2.0697	0.1875
No log	8.0	80	2.0656	0.1875
No log	9.0	90	2.0605	0.2125
No log	10.0	100	2.0540	0.2313
No log	11.0	110	2.0462	0.2625
No log	12.0	120	2.0369	0.2687
No log	13.0	130	2.0259	0.2687
No log	14.0	140	2.0117	0.2687
No log	15.0	150	1.9947	0.3125
No log	16.0	160	1.9763	0.2938
No log	17.0	170	1.9547	0.3125
No log	18.0	180	1.9313	0.325
No log	19.0	190	1.9075	0.35
No log	20.0	200	1.8817	0.3563
No log	21.0	210	1.8535	0.3812
No log	22.0	220	1.8244	0.4062
No log	23.0	230	1.7954	0.4188
No log	24.0	240	1.7664	0.4375
No log	25.0	250	1.7380	0.45

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.19.1