metadata
library_name: transformers
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: 0.6125
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: 1.1555
- Accuracy: 0.6125
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 25
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.7108 | 1.0 | 10 | 1.8424 | 0.4188 |
| 1.6278 | 2.0 | 20 | 1.7495 | 0.45 |
| 1.465 | 3.0 | 30 | 1.6153 | 0.5062 |
| 1.2862 | 4.0 | 40 | 1.5099 | 0.55 |
| 1.1151 | 5.0 | 50 | 1.4399 | 0.5312 |
| 0.9631 | 6.0 | 60 | 1.3803 | 0.5375 |
| 0.8242 | 7.0 | 70 | 1.3213 | 0.5875 |
| 0.6939 | 8.0 | 80 | 1.2673 | 0.575 |
| 0.576 | 9.0 | 90 | 1.2463 | 0.5938 |
| 0.4801 | 10.0 | 100 | 1.2108 | 0.6 |
| 0.4008 | 11.0 | 110 | 1.2093 | 0.575 |
| 0.3426 | 12.0 | 120 | 1.1744 | 0.5687 |
| 0.2976 | 13.0 | 130 | 1.1710 | 0.5938 |
| 0.2667 | 14.0 | 140 | 1.1545 | 0.5875 |
| 0.2434 | 15.0 | 150 | 1.1622 | 0.6 |
| 0.2261 | 16.0 | 160 | 1.1522 | 0.5875 |
| 0.2119 | 17.0 | 170 | 1.1486 | 0.6062 |
| 0.2016 | 18.0 | 180 | 1.1555 | 0.6125 |
| 0.1932 | 19.0 | 190 | 1.1487 | 0.6062 |
| 0.1857 | 20.0 | 200 | 1.1422 | 0.5938 |
| 0.1812 | 21.0 | 210 | 1.1438 | 0.6 |
| 0.1772 | 22.0 | 220 | 1.1521 | 0.5687 |
| 0.1735 | 23.0 | 230 | 1.1428 | 0.5938 |
| 0.1714 | 24.0 | 240 | 1.1487 | 0.6 |
| 0.1703 | 25.0 | 250 | 1.1462 | 0.6 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1