metadata
base_model: google/vit-base-patch16-224-in21k
datasets:
- imagefolder
license: apache-2.0
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: results
results:
- task:
type: image-classification
name: Image Classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- type: accuracy
value: 0.49375
name: Accuracy
results
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: 1.6499
- Accuracy: 0.4938
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.0569 | 1.0 | 20 | 2.0360 | 0.1938 |
| 1.9499 | 2.0 | 40 | 1.9751 | 0.325 |
| 1.8401 | 3.0 | 60 | 1.8969 | 0.4125 |
| 1.7302 | 4.0 | 80 | 1.8159 | 0.4625 |
| 1.6452 | 5.0 | 100 | 1.7533 | 0.4437 |
| 1.5509 | 6.0 | 120 | 1.7124 | 0.4938 |
| 1.4928 | 7.0 | 140 | 1.6806 | 0.5125 |
| 1.4412 | 8.0 | 160 | 1.6631 | 0.4938 |
| 1.407 | 9.0 | 180 | 1.6530 | 0.5 |
| 1.4025 | 10.0 | 200 | 1.6499 | 0.4938 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1