metadata

license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - f1
  - accuracy
model-index:
  - name: vedt-lg
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train
          args: default
        metrics:
          - name: F1
            type: f1
            value: 0.95
          - name: Accuracy
            type: accuracy
            value: 0.94

vedt-lg

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

Loss: 0.1643
F1: 0.95
Roc Auc: 0.96
Accuracy: 0.94

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: 8
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
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	F1	Roc Auc	Accuracy
0.523	1.0	122	0.5292	0.53	0.67	0.45
0.3308	2.0	245	0.3331	0.82	0.86	0.79
0.1989	3.0	367	0.2265	0.91	0.93	0.9
0.1182	4.0	490	0.1949	0.92	0.94	0.92
0.0936	4.98	610	0.1643	0.95	0.96	0.94

Framework versions

Transformers 4.38.2
Pytorch 2.2.0
Datasets 2.16.1
Tokenizers 0.15.1