Hugging Face's logo

sudo-s
/
robot22

Image Classification
Transformers
PyTorch
TensorBoard
vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
robot22 / README.md
sudo-s's picture
sudo-s
update model card README.md
d2f10a8
preview code
|
raw
history blame contribute delete
1.6 kB
metadata
license: apache-2.0
tags:
  - image-classification
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: robot22
    results: []

robot22

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the sudo-s/herbier_mesuem6 dataset. It achieves the following results on the evaluation set:

  • Loss: 2.5674
  • Accuracy: 0.5077

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: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
3.9154 0.23 100 3.8417 0.2213
3.1764 0.47 200 3.2243 0.3201
2.8186 0.7 300 2.7973 0.4284
2.632 0.93 400 2.5674 0.5077

Framework versions

  • Transformers 4.20.1
  • Pytorch 1.12.0
  • Datasets 2.3.2
  • Tokenizers 0.12.1