metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch32-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: results
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: 0.45625
results
This model is a fine-tuned version of google/vit-base-patch32-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.4692
- Accuracy: 0.4562
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7426 | 1.0 | 40 | 1.4692 | 0.4562 |
| 0.4647 | 2.0 | 80 | 1.5033 | 0.4313 |
| 0.2527 | 3.0 | 120 | 1.5517 | 0.4813 |
| 0.1551 | 4.0 | 160 | 1.6071 | 0.4688 |
| 0.113 | 5.0 | 200 | 1.6474 | 0.475 |
| 0.0914 | 6.0 | 240 | 1.6752 | 0.45 |
| 0.0774 | 7.0 | 280 | 1.7003 | 0.45 |
| 0.0698 | 8.0 | 320 | 1.7336 | 0.4437 |
| 0.063 | 9.0 | 360 | 1.7595 | 0.45 |
| 0.0583 | 10.0 | 400 | 1.7778 | 0.4437 |
| 0.0551 | 11.0 | 440 | 1.7938 | 0.4375 |
| 0.0531 | 12.0 | 480 | 1.8082 | 0.4375 |
| 0.0509 | 13.0 | 520 | 1.8176 | 0.4437 |
| 0.0499 | 14.0 | 560 | 1.8230 | 0.4375 |
| 0.0494 | 15.0 | 600 | 1.8249 | 0.4375 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1
- Datasets 2.21.0
- Tokenizers 0.19.1