metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: image_classification
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: en-US
split: train
args: en-US
metrics:
- name: Accuracy
type: accuracy
value: 0.575
image_classification
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: 1.5646
- Accuracy: 0.575
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: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 40 | 1.8666 | 0.3312 |
| No log | 2.0 | 80 | 1.5679 | 0.4188 |
| No log | 3.0 | 120 | 1.4168 | 0.5062 |
| No log | 4.0 | 160 | 1.2966 | 0.5563 |
| No log | 5.0 | 200 | 1.3039 | 0.45 |
| No log | 6.0 | 240 | 1.2528 | 0.5188 |
| No log | 7.0 | 280 | 1.2559 | 0.525 |
| No log | 8.0 | 320 | 1.2510 | 0.55 |
| No log | 9.0 | 360 | 1.3209 | 0.525 |
| No log | 10.0 | 400 | 1.2598 | 0.5188 |
| No log | 11.0 | 440 | 1.3478 | 0.5 |
| No log | 12.0 | 480 | 1.2411 | 0.5625 |
| 1.0456 | 13.0 | 520 | 1.2945 | 0.575 |
| 1.0456 | 14.0 | 560 | 1.3332 | 0.5 |
| 1.0456 | 15.0 | 600 | 1.2186 | 0.5875 |
| 1.0456 | 16.0 | 640 | 1.2907 | 0.5563 |
| 1.0456 | 17.0 | 680 | 1.3378 | 0.5312 |
| 1.0456 | 18.0 | 720 | 1.4472 | 0.5375 |
| 1.0456 | 19.0 | 760 | 1.1642 | 0.6438 |
| 1.0456 | 20.0 | 800 | 1.2972 | 0.5437 |
| 1.0456 | 21.0 | 840 | 1.3696 | 0.5875 |
| 1.0456 | 22.0 | 880 | 1.4568 | 0.5375 |
| 1.0456 | 23.0 | 920 | 1.3409 | 0.5625 |
| 1.0456 | 24.0 | 960 | 1.3188 | 0.5687 |
| 0.2919 | 25.0 | 1000 | 1.4131 | 0.5813 |
| 0.2919 | 26.0 | 1040 | 1.3066 | 0.575 |
| 0.2919 | 27.0 | 1080 | 1.4908 | 0.5375 |
| 0.2919 | 28.0 | 1120 | 1.4409 | 0.5563 |
| 0.2919 | 29.0 | 1160 | 1.5531 | 0.5188 |
| 0.2919 | 30.0 | 1200 | 1.4412 | 0.5938 |
| 0.2919 | 31.0 | 1240 | 1.4300 | 0.575 |
| 0.2919 | 32.0 | 1280 | 1.6232 | 0.5375 |
| 0.2919 | 33.0 | 1320 | 1.4592 | 0.6 |
| 0.2919 | 34.0 | 1360 | 1.3311 | 0.6312 |
| 0.2919 | 35.0 | 1400 | 1.5094 | 0.5625 |
| 0.2919 | 36.0 | 1440 | 1.3694 | 0.6062 |
| 0.2919 | 37.0 | 1480 | 1.5205 | 0.5813 |
| 0.1643 | 38.0 | 1520 | 1.4502 | 0.6125 |
| 0.1643 | 39.0 | 1560 | 1.2809 | 0.6625 |
| 0.1643 | 40.0 | 1600 | 1.6043 | 0.5563 |
| 0.1643 | 41.0 | 1640 | 1.5729 | 0.5625 |
| 0.1643 | 42.0 | 1680 | 1.5918 | 0.5625 |
| 0.1643 | 43.0 | 1720 | 1.5747 | 0.575 |
| 0.1643 | 44.0 | 1760 | 1.6325 | 0.5437 |
| 0.1643 | 45.0 | 1800 | 1.5850 | 0.575 |
| 0.1643 | 46.0 | 1840 | 1.6558 | 0.575 |
| 0.1643 | 47.0 | 1880 | 1.4821 | 0.5875 |
| 0.1643 | 48.0 | 1920 | 1.6070 | 0.575 |
| 0.1643 | 49.0 | 1960 | 1.6660 | 0.525 |
| 0.1152 | 50.0 | 2000 | 1.5803 | 0.575 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3