metadata

license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - image-classification
  - generated_from_trainer
datasets:
  - renovation
metrics:
  - accuracy
model-index:
  - name: vit-base-renovation2
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: renovations
          type: renovation
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.6666666666666666

vit-base-renovation2

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

Loss: 0.8273
Accuracy: 0.6667

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: 4
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.359	0.2	25	1.2074	0.4658
1.1384	0.4	50	1.1213	0.5205
1.0866	0.6	75	0.9746	0.6301
1.1787	0.81	100	1.0523	0.5662
0.9242	1.01	125	0.9543	0.6256
0.7945	1.21	150	0.9200	0.6119
0.8379	1.41	175	0.8447	0.6712
0.7253	1.61	200	0.8642	0.6575
0.6344	1.81	225	0.8443	0.6438
0.6521	2.02	250	0.8273	0.6667
0.3627	2.22	275	0.8653	0.6712
0.2523	2.42	300	0.8748	0.6895
0.363	2.62	325	0.8407	0.6849
0.3433	2.82	350	0.9696	0.6484
0.2874	3.02	375	0.9290	0.6804
0.1682	3.23	400	0.9713	0.6575
0.1575	3.43	425	0.9963	0.6804
0.0822	3.63	450	0.9473	0.7123
0.1678	3.83	475	0.9788	0.7032

Framework versions

Transformers 4.39.1
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2