metadata

license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: attraction-classifier
    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: 0.809322033898305

attraction-classifier

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: 0.5064
Accuracy: 0.8093

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: 32
eval_batch_size: 32
seed: 69
gradient_accumulation_steps: 8
total_train_batch_size: 256
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.05
num_epochs: 25
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4908	3.01	50	0.5141	0.7797
0.3766	6.02	100	0.4485	0.7839
0.3121	9.02	150	0.4550	0.7903
0.2569	12.03	200	0.3977	0.8305
0.215	15.04	250	0.4732	0.7987
0.186	18.05	300	0.4804	0.8072
0.1568	21.05	350	0.5064	0.8093

Framework versions

Transformers 4.37.2
Pytorch 2.0.1+cu117
Datasets 2.15.0
Tokenizers 0.15.0