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: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.565
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: 2.0792
- Accuracy: 0.565
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: 5
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.8643 | 0.55 | 100 | 1.7445 | 0.45 |
0.3609 | 1.09 | 200 | 1.4977 | 0.565 |
0.2602 | 1.64 | 300 | 1.8113 | 0.525 |
0.1278 | 2.19 | 400 | 1.8174 | 0.53 |
0.051 | 2.73 | 500 | 1.9151 | 0.525 |
0.0619 | 3.28 | 600 | 2.0656 | 0.55 |
0.0263 | 3.83 | 700 | 2.1127 | 0.555 |
0.0104 | 4.37 | 800 | 2.1411 | 0.55 |
0.01 | 4.92 | 900 | 2.0792 | 0.565 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0