metadata

license: apache-2.0
base_model: google/vit-base-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: 0.61875

image_classification

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: 1.2094
Accuracy: 0.6188

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: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
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
1.8174	1.0	10	1.8349	0.4062
1.7364	2.0	20	1.6966	0.4
1.6087	3.0	30	1.5892	0.45
1.4904	4.0	40	1.4914	0.4875
1.4009	5.0	50	1.4288	0.5125
1.3129	6.0	60	1.3619	0.575
1.2233	7.0	70	1.3622	0.5687
1.1419	8.0	80	1.3047	0.5188
1.094	9.0	90	1.2763	0.6062
1.0366	10.0	100	1.2496	0.5625
0.9785	11.0	110	1.2368	0.6
0.9435	12.0	120	1.1960	0.6438
0.9031	13.0	130	1.2083	0.5563
0.8829	14.0	140	1.2629	0.5188
0.824	15.0	150	1.2061	0.5938
0.7952	16.0	160	1.2630	0.55
0.7744	17.0	170	1.2329	0.5625
0.7487	18.0	180	1.2259	0.5437
0.7381	19.0	190	1.1750	0.5813
0.7261	20.0	200	1.1802	0.575

Framework versions

Transformers 4.33.1
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3