metadata

license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: xyz
    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: 0.9101851851851852

xyz

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: 0.3224
Accuracy: 0.9102

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: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.2269	0.37	100	1.2058	0.6019
1.0891	0.74	200	0.9254	0.7046
0.5328	1.11	300	0.7417	0.7741
0.5259	1.48	400	0.7145	0.7722
0.4889	1.85	500	0.5621	0.825
0.2753	2.22	600	0.5251	0.8444
0.2569	2.59	700	0.5792	0.8259
0.2251	2.96	800	0.4169	0.8731
0.086	3.33	900	0.4182	0.8843
0.1352	3.7	1000	0.3711	0.8880
0.0608	4.07	1100	0.3430	0.9046
0.0175	4.44	1200	0.3241	0.9185
0.0149	4.81	1300	0.3224	0.9102

Framework versions

Transformers 4.38.2
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2