metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- image-classification
- vision
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: TransparentBagClassifier
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8597560975609756
TransparentBagClassifier
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.3956
- Accuracy: 0.8598
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 | Accuracy | Validation Loss |
|---|---|---|---|---|
| 0.448 | 1.0 | 82 | 0.7304 | 0.5725 |
| 0.5097 | 2.0 | 164 | 0.7652 | 0.4946 |
| 0.452 | 3.0 | 246 | 0.7565 | 0.4841 |
| 0.3885 | 4.0 | 328 | 0.7565 | 0.4812 |
| 0.4743 | 5.0 | 410 | 0.7739 | 0.4626 |
| 0.4749 | 4.0 | 464 | 0.4572 | 0.7988 |
| 0.4319 | 5.0 | 580 | 0.3956 | 0.8598 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cpu
- Datasets 3.0.0
- Tokenizers 0.19.1