metadata

library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: ViT-threat-classification
    results: []

ViT-threat-classification

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on a threat classification dataset. This model was created for a Carleton University computer vision hacking event and serves as a proof of concept rather than complete model. It is trained on an extremely small and limited dataset and the performance is limited. It achieves the following results on the evaluation set:

Loss: 0.4568
Accuracy: 1.0

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: 1e-06
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.328	0.9756	10	0.4556	0.875
0.3226	1.9512	20	0.4736	0.75
0.3619	2.9268	30	0.4568	1.0

Framework versions

Transformers 4.46.2
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.20.3