metadata

library_name: peft
license: apache-2.0
base_model: google/vit-large-patch16-224
tags:
  - image-classification
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: vit-large-patch16-224-testing-dungeons-lora-23Nov24-008
    results:
      - task:
          type: image-classification
          name: Image Classification
        dataset:
          name: rotated_maps
          type: imagefolder
          config: default
          split: validation
          args: default
        metrics:
          - type: accuracy
            value: 0.9629629629629629
            name: Accuracy

vit-large-patch16-224-testing-dungeons-lora-23Nov24-008

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

Loss: 0.2048
Accuracy: 0.9630

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: 0.005
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.6667	1	1.5395	0.1852
No log	2.0	3	1.2052	0.4815
No log	2.6667	4	1.1291	0.5185
No log	4.0	6	0.4352	0.8148
No log	4.6667	7	0.3886	0.9259
No log	6.0	9	0.2470	0.9630
0.9407	6.6667	10	0.2048	0.9630

Framework versions

PEFT 0.13.2
Transformers 4.46.2
Pytorch 2.5.1+cu121
Datasets 3.1.0
Tokenizers 0.20.3