metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: xyz
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: 0.9018518518518519
xyz
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: 0.4588
- Accuracy: 0.9019
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: 48
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.1739 | 1.11 | 100 | 0.5771 | 0.8407 |
0.0677 | 2.22 | 200 | 0.5907 | 0.8519 |
0.0699 | 3.33 | 300 | 0.4160 | 0.8870 |
0.0598 | 4.44 | 400 | 0.7336 | 0.8380 |
0.0108 | 5.56 | 500 | 0.5133 | 0.8898 |
0.0082 | 6.67 | 600 | 0.4786 | 0.8981 |
0.0031 | 7.78 | 700 | 0.4624 | 0.9009 |
0.0046 | 8.89 | 800 | 0.4594 | 0.9 |
0.0052 | 10.0 | 900 | 0.4588 | 0.9019 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0