metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: results
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.59375
results
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: 1.1778
- Accuracy: 0.5938
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.7091 | 1.0 | 40 | 1.5245 | 0.4313 |
| 1.2646 | 2.0 | 80 | 1.3654 | 0.5 |
| 0.8405 | 3.0 | 120 | 1.2695 | 0.4938 |
| 0.441 | 4.0 | 160 | 1.1778 | 0.5938 |
| 0.2931 | 5.0 | 200 | 1.3847 | 0.5625 |
| 0.1199 | 6.0 | 240 | 1.4813 | 0.5687 |
| 0.0417 | 7.0 | 280 | 1.5159 | 0.5938 |
| 0.0309 | 8.0 | 320 | 1.4851 | 0.6125 |
| 0.0245 | 9.0 | 360 | 1.5161 | 0.6188 |
| 0.021 | 10.0 | 400 | 1.5315 | 0.6188 |
| 0.0193 | 11.0 | 440 | 1.5456 | 0.6438 |
| 0.0174 | 12.0 | 480 | 1.5714 | 0.6312 |
| 0.023 | 13.0 | 520 | 1.5815 | 0.6312 |
| 0.0216 | 14.0 | 560 | 1.5951 | 0.6375 |
| 0.0202 | 15.0 | 600 | 1.5938 | 0.6312 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1