metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- beans
metrics:
- accuracy
model-index:
- name: beans_image_classification
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: beans
type: beans
config: default
split: train[:500]
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.96
beans_image_classification
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: 0.1072
- Accuracy: 0.96
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: 0.001
- train_batch_size: 12
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 48
- 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 |
|---|---|---|---|---|
| No log | 0.94 | 8 | 1.3666 | 0.66 |
| 0.3651 | 2.0 | 17 | 0.3823 | 0.84 |
| 0.5622 | 2.94 | 25 | 0.3333 | 0.86 |
| 0.3373 | 4.0 | 34 | 0.1274 | 0.97 |
| 0.2055 | 4.94 | 42 | 0.1882 | 0.93 |
| 0.1819 | 6.0 | 51 | 0.2265 | 0.9 |
| 0.1819 | 6.94 | 59 | 0.2395 | 0.91 |
| 0.2428 | 8.0 | 68 | 0.1451 | 0.97 |
| 0.1305 | 8.94 | 76 | 0.1554 | 0.94 |
| 0.1203 | 9.41 | 80 | 0.1705 | 0.92 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1