metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- image-classification
- generated_from_trainer
datasets:
- renovation
metrics:
- accuracy
model-index:
- name: vit-base-beans-demo-v5
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: beans
type: renovation
config: default
split: validation
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.6575342465753424
vit-base-beans-demo-v5
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the beans dataset. It achieves the following results on the evaluation set:
- Loss: 0.7925
- Accuracy: 0.6575
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1711 | 0.81 | 100 | 1.0255 | 0.5982 |
| 0.7083 | 1.61 | 200 | 0.7925 | 0.6575 |
| 0.2479 | 2.42 | 300 | 0.8712 | 0.6941 |
| 0.127 | 3.23 | 400 | 0.8440 | 0.6941 |
Framework versions
- Transformers 4.39.1
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2