metadata

license: apache-2.0
base_model: WinKawaks/vit-small-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: msi-vit-small-pretrain
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.6280752026838132

msi-vit-small-pretrain

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

Loss: 2.9496
Accuracy: 0.6281

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: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1838	1.0	1008	1.0518	0.6251
0.1096	2.0	2016	1.2599	0.6535
0.0547	3.0	3024	1.9005	0.6331
0.0415	4.0	4032	2.5122	0.6327
0.0163	5.0	5040	2.9496	0.6281

Framework versions

Transformers 4.36.0
Pytorch 2.0.1+cu117
Datasets 2.15.0
Tokenizers 0.15.0