metadata
license: apache-2.0
tags:
- image-classification
- vision
- generated_from_trainer
datasets:
- beans
metrics:
- accuracy
model-index:
- name: vit-base-beans
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: beans
type: beans
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9924812030075187
vit-base-beans
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: 0.0824
- Accuracy: 0.9925
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 1337
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3039 | 1.0 | 130 | 0.2474 | 0.9624 |
| 0.1299 | 2.0 | 260 | 0.1007 | 0.9925 |
| 0.0885 | 3.0 | 390 | 0.0824 | 0.9925 |
| 0.0976 | 4.0 | 520 | 0.1179 | 0.9699 |
| 0.1284 | 5.0 | 650 | 0.0832 | 0.9774 |
Framework versions
- Transformers 4.23.0.dev0
- Pytorch 1.12.1+cu113
- Datasets 2.5.2
- Tokenizers 0.13.1