metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit-base-game-icons
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: game-icons
split: train
args: game-icons
metrics:
- name: Accuracy
type: accuracy
value: 0.6548387096774193
vit-base-game-icons
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: 1.1693
- Accuracy: 0.6548
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 1337
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.3532 | 1.0 | 440 | 1.4272 | 0.6 |
| 1.2843 | 2.0 | 880 | 1.2953 | 0.6032 |
| 1.1254 | 3.0 | 1320 | 1.2201 | 0.6339 |
| 1.5579 | 4.0 | 1760 | 1.1343 | 0.6677 |
| 1.2813 | 5.0 | 2200 | 1.1693 | 0.6548 |
Framework versions
- Transformers 4.28.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.9.0
- Tokenizers 0.12.1