Hugging Face's logo

DazMashaly
/
VIT_large_ieee

Image Classification
Transformers
PyTorch
vit
Generated from Trainer
Inference Endpoints
Model card Files Community
1
VIT_large_ieee / README.md
DazMashaly's picture
DazMashaly
Update README.md
f22b957
preview code
|
raw
history blame contribute delete
1.51 kB
metadata
license: apache-2.0
base_model: google/vit-large-patch16-224-in21k
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: VIT_large_ieee
    results: []

VIT_large_ieee

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

  • Loss: 0.0230
  • Accuracy: 0.9941

Model description

This model was used for IEEE ManSB VICTORIS 2.0 Final Competition

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: 1e-06
  • 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: 2

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.0047 0.67 100 0.0283 0.9929
0.0165 1.34 200 0.0230 0.9941

Framework versions

  • Transformers 4.33.1
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3