metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- image_folder
metrics:
- accuracy
model-index:
- name: vit-base-patch16-224-in21k-finetuned-cassava
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: image_folder
type: image_folder
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8705607476635514
vit-base-patch16-224-in21k-finetuned-cassava
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: 0.3742
- Accuracy: 0.8706
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 |
|---|---|---|---|---|
| 0.5628 | 1.0 | 150 | 0.5357 | 0.8308 |
| 0.4398 | 2.0 | 300 | 0.4311 | 0.8598 |
| 0.4022 | 3.0 | 450 | 0.3958 | 0.8668 |
| 0.3855 | 4.0 | 600 | 0.4030 | 0.8598 |
| 0.3659 | 5.0 | 750 | 0.4125 | 0.8617 |
| 0.3393 | 6.0 | 900 | 0.3840 | 0.8673 |
| 0.3022 | 7.0 | 1050 | 0.3775 | 0.8673 |
| 0.2941 | 8.0 | 1200 | 0.3742 | 0.8706 |
| 0.2903 | 9.0 | 1350 | 0.3809 | 0.8696 |
| 0.2584 | 10.0 | 1500 | 0.3756 | 0.8696 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1