|
---
|
|
license: apache-2.0
|
|
base_model: google/vit-base-patch16-224
|
|
tags:
|
|
- generated_from_trainer
|
|
datasets:
|
|
- imagefolder
|
|
metrics:
|
|
- accuracy
|
|
model-index:
|
|
- name: vit-base-patch16-224-ve-U13b-R
|
|
results:
|
|
- task:
|
|
name: Image Classification
|
|
type: image-classification
|
|
dataset:
|
|
name: imagefolder
|
|
type: imagefolder
|
|
config: default
|
|
split: validation
|
|
args: default
|
|
metrics:
|
|
- name: Accuracy
|
|
type: accuracy
|
|
value: 0.9347826086956522
|
|
---
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
should probably proofread and complete it, then remove this comment. -->
|
|
|
|
# vit-base-patch16-224-ve-U13b-R
|
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 0.3534
|
|
- Accuracy: 0.9348
|
|
|
|
## 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: 5.5e-05
|
|
- train_batch_size: 8
|
|
- eval_batch_size: 8
|
|
- seed: 42
|
|
- gradient_accumulation_steps: 2
|
|
- total_train_batch_size: 16
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
- lr_scheduler_type: linear
|
|
- lr_scheduler_warmup_ratio: 0.05
|
|
- num_epochs: 40
|
|
|
|
### Training results
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
|
| 1.3157 | 0.99 | 51 | 1.2967 | 0.3478 |
|
|
| 0.9801 | 2.0 | 103 | 0.9966 | 0.5870 |
|
|
| 0.7385 | 2.99 | 154 | 0.7600 | 0.7174 |
|
|
| 0.572 | 4.0 | 206 | 0.6425 | 0.7826 |
|
|
| 0.3646 | 4.99 | 257 | 0.7687 | 0.6957 |
|
|
| 0.3033 | 6.0 | 309 | 0.6336 | 0.7391 |
|
|
| 0.3073 | 6.99 | 360 | 0.3534 | 0.9348 |
|
|
| 0.1623 | 8.0 | 412 | 0.8559 | 0.6739 |
|
|
| 0.1079 | 8.99 | 463 | 0.9730 | 0.7391 |
|
|
| 0.2703 | 10.0 | 515 | 0.7768 | 0.8043 |
|
|
| 0.178 | 10.99 | 566 | 0.8520 | 0.7826 |
|
|
| 0.2191 | 12.0 | 618 | 1.0049 | 0.7391 |
|
|
| 0.0597 | 12.99 | 669 | 0.8334 | 0.7609 |
|
|
| 0.0881 | 14.0 | 721 | 0.9985 | 0.7609 |
|
|
| 0.1265 | 14.99 | 772 | 0.9443 | 0.8043 |
|
|
| 0.0696 | 16.0 | 824 | 0.9878 | 0.8261 |
|
|
| 0.1198 | 16.99 | 875 | 0.8784 | 0.8043 |
|
|
| 0.1484 | 18.0 | 927 | 0.9595 | 0.7609 |
|
|
| 0.2887 | 18.99 | 978 | 1.0563 | 0.8043 |
|
|
| 0.1423 | 20.0 | 1030 | 0.8550 | 0.8043 |
|
|
| 0.083 | 20.99 | 1081 | 0.9093 | 0.7826 |
|
|
| 0.0695 | 22.0 | 1133 | 1.2758 | 0.6739 |
|
|
| 0.0285 | 22.99 | 1184 | 1.0852 | 0.7609 |
|
|
| 0.0132 | 24.0 | 1236 | 1.3341 | 0.6957 |
|
|
| 0.0957 | 24.99 | 1287 | 1.1965 | 0.7391 |
|
|
| 0.0633 | 26.0 | 1339 | 1.1199 | 0.7609 |
|
|
| 0.0705 | 26.99 | 1390 | 1.0551 | 0.8043 |
|
|
| 0.0564 | 28.0 | 1442 | 1.4332 | 0.7391 |
|
|
| 0.0798 | 28.99 | 1493 | 1.3855 | 0.7391 |
|
|
| 0.0326 | 30.0 | 1545 | 1.0534 | 0.8043 |
|
|
| 0.092 | 30.99 | 1596 | 1.1745 | 0.7609 |
|
|
| 0.1243 | 32.0 | 1648 | 1.1341 | 0.8043 |
|
|
| 0.062 | 32.99 | 1699 | 1.2648 | 0.7826 |
|
|
| 0.0941 | 34.0 | 1751 | 1.1236 | 0.7826 |
|
|
| 0.0119 | 34.99 | 1802 | 1.1303 | 0.8043 |
|
|
| 0.044 | 36.0 | 1854 | 1.1848 | 0.7826 |
|
|
| 0.0073 | 36.99 | 1905 | 1.1796 | 0.7609 |
|
|
| 0.0149 | 38.0 | 1957 | 1.2491 | 0.7826 |
|
|
| 0.0194 | 38.99 | 2008 | 1.1812 | 0.7826 |
|
|
| 0.0577 | 39.61 | 2040 | 1.1777 | 0.7609 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.36.2
|
|
- Pytorch 2.1.2+cu118
|
|
- Datasets 2.16.1
|
|
- Tokenizers 0.15.0
|
|
|
