Hugging Face's logo

skutaada
/
VIT-VGGFace

Image Classification
Transformers
Safetensors
vit
Generated from Trainer
Inference Endpoints
Model card Files Community
VIT-VGGFace / README.md
skutaada's picture
skutaada
End of training
7d8251f verified
preview code
|
raw
history blame
1.75 kB
metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: ViT-VGGFace
    results: []

ViT-VGGFace

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

  • Loss: 2.4284
  • Accuracy: 0.6615

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: 24
  • eval_batch_size: 24
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 96
  • 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
5.1532 0.9982 416 5.0937 0.1848
3.8037 1.9988 833 3.7332 0.4684
3.0074 2.9994 1250 2.9895 0.5756
2.5421 4.0 1667 2.5881 0.634
2.4549 4.9910 2080 2.4284 0.6615

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.3.1+rocm6.0
  • Datasets 2.20.0
  • Tokenizers 0.19.1