metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- AI-Lab-Makerere/beans
metrics:
- matthews_correlation
base_model: google/vit-base-patch16-224-in21k
model-index:
- name: Model_folder
results:
- task:
type: image-classification
name: Image Classification
dataset:
name: beans
type: beans
config: default
split: validation
args: default
metrics:
- type: matthews_correlation
value: 0.9888050243347044
name: Matthews Correlation
Model_folder
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: 0.0171
- Matthews Correlation: 0.9888
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: 32
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| 0.0488 | 0.91 | 30 | 0.1366 | 0.9449 |
| 0.0077 | 1.82 | 60 | 0.0508 | 0.9775 |
| 0.0057 | 2.73 | 90 | 0.0366 | 0.9888 |
| 0.0042 | 3.64 | 120 | 0.0171 | 0.9888 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1