metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- image_folder
metrics:
- accuracy
model-index:
- name: vit-base-patch16-224-in21k-finetuned-cassava3
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: image_folder
type: image_folder
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8852803738317757
vit-base-patch16-224-in21k-finetuned-cassava3
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the image_folder dataset. It achieves the following results on the evaluation set:
- Loss: 0.3403
- Accuracy: 0.8853
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5624 | 0.99 | 133 | 0.5866 | 0.8166 |
| 0.4717 | 1.99 | 266 | 0.4245 | 0.8692 |
| 0.4105 | 2.99 | 399 | 0.3708 | 0.8811 |
| 0.3753 | 3.99 | 532 | 0.3646 | 0.8787 |
| 0.2997 | 4.99 | 665 | 0.3655 | 0.8780 |
| 0.3176 | 5.99 | 798 | 0.3545 | 0.8822 |
| 0.2849 | 6.99 | 931 | 0.3441 | 0.8850 |
| 0.2931 | 7.99 | 1064 | 0.3419 | 0.8855 |
| 0.27 | 8.99 | 1197 | 0.3419 | 0.8848 |
| 0.2927 | 9.99 | 1330 | 0.3403 | 0.8853 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1