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: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.4875
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: 1.4148
- Accuracy: 0.4875
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-06
- 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 | 2.0788 | 0.1125 |
| No log | 2.0 | 80 | 2.0706 | 0.1688 |
| No log | 3.0 | 120 | 2.0465 | 0.2062 |
| No log | 4.0 | 160 | 2.0386 | 0.2 |
| No log | 5.0 | 200 | 2.0110 | 0.2188 |
| No log | 6.0 | 240 | 1.9815 | 0.225 |
| No log | 7.0 | 280 | 1.9430 | 0.2313 |
| No log | 8.0 | 320 | 1.8889 | 0.3312 |
| No log | 9.0 | 360 | 1.8283 | 0.3063 |
| No log | 10.0 | 400 | 1.7769 | 0.3438 |
| No log | 11.0 | 440 | 1.7292 | 0.325 |
| No log | 12.0 | 480 | 1.6966 | 0.3312 |
| 1.885 | 13.0 | 520 | 1.6708 | 0.375 |
| 1.885 | 14.0 | 560 | 1.6527 | 0.3937 |
| 1.885 | 15.0 | 600 | 1.6266 | 0.3937 |
| 1.885 | 16.0 | 640 | 1.6116 | 0.3937 |
| 1.885 | 17.0 | 680 | 1.5944 | 0.4188 |
| 1.885 | 18.0 | 720 | 1.5931 | 0.3688 |
| 1.885 | 19.0 | 760 | 1.5645 | 0.3937 |
| 1.885 | 20.0 | 800 | 1.5503 | 0.45 |
| 1.885 | 21.0 | 840 | 1.5550 | 0.425 |
| 1.885 | 22.0 | 880 | 1.5370 | 0.4375 |
| 1.885 | 23.0 | 920 | 1.5239 | 0.4688 |
| 1.885 | 24.0 | 960 | 1.5240 | 0.4437 |
| 1.4797 | 25.0 | 1000 | 1.5031 | 0.4688 |
| 1.4797 | 26.0 | 1040 | 1.5183 | 0.4188 |
| 1.4797 | 27.0 | 1080 | 1.4949 | 0.4062 |
| 1.4797 | 28.0 | 1120 | 1.5014 | 0.4437 |
| 1.4797 | 29.0 | 1160 | 1.4766 | 0.4625 |
| 1.4797 | 30.0 | 1200 | 1.4892 | 0.4375 |
| 1.4797 | 31.0 | 1240 | 1.4812 | 0.4938 |
| 1.4797 | 32.0 | 1280 | 1.4472 | 0.4688 |
| 1.4797 | 33.0 | 1320 | 1.4744 | 0.425 |
| 1.4797 | 34.0 | 1360 | 1.4563 | 0.4562 |
| 1.4797 | 35.0 | 1400 | 1.4785 | 0.4313 |
| 1.4797 | 36.0 | 1440 | 1.4331 | 0.5125 |
| 1.4797 | 37.0 | 1480 | 1.4551 | 0.45 |
| 1.293 | 38.0 | 1520 | 1.4470 | 0.4625 |
| 1.293 | 39.0 | 1560 | 1.4695 | 0.4375 |
| 1.293 | 40.0 | 1600 | 1.4366 | 0.4813 |
| 1.293 | 41.0 | 1640 | 1.4350 | 0.5 |
| 1.293 | 42.0 | 1680 | 1.4181 | 0.475 |
| 1.293 | 43.0 | 1720 | 1.4428 | 0.4875 |
| 1.293 | 44.0 | 1760 | 1.4067 | 0.5188 |
| 1.293 | 45.0 | 1800 | 1.4058 | 0.475 |
| 1.293 | 46.0 | 1840 | 1.4341 | 0.475 |
| 1.293 | 47.0 | 1880 | 1.4082 | 0.4813 |
| 1.293 | 48.0 | 1920 | 1.4461 | 0.4688 |
| 1.293 | 49.0 | 1960 | 1.4136 | 0.5062 |
| 1.1998 | 50.0 | 2000 | 1.4226 | 0.4938 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2