metadata

license: apache-2.0
base_model: google/vit-large-patch16-224-in21k
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: image_classification
    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: 0.51875

image_classification

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

Loss: 1.5386
Accuracy: 0.5188

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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.0473	1.0	20	2.0179	0.175
1.6184	2.0	40	1.7787	0.2437
1.2134	3.0	60	1.5985	0.3625
1.0157	4.0	80	1.3311	0.4813
0.8578	5.0	100	1.3041	0.4875
0.6496	6.0	120	1.3222	0.5062
0.5972	7.0	140	1.5594	0.4562
0.5073	8.0	160	1.4126	0.4813
0.3964	9.0	180	1.3702	0.525
0.4054	10.0	200	1.3894	0.5188
0.2845	11.0	220	1.4471	0.5188
0.2262	12.0	240	1.5165	0.525
0.2412	13.0	260	1.4684	0.5125
0.2229	14.0	280	1.4005	0.525
0.2078	15.0	300	1.5629	0.5062
0.1619	16.0	320	1.6014	0.525
0.1834	17.0	340	1.4821	0.5125
0.1594	18.0	360	1.5195	0.5375
0.1249	19.0	380	1.5585	0.5188
0.1117	20.0	400	1.4735	0.5687

Framework versions

Transformers 4.42.4
Pytorch 2.4.0+cu121
Datasets 2.21.0
Tokenizers 0.19.1