|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch32-384 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: rmsProps_VitB-p32-384-1e-4-batch_32_epoch_4_classes_24 |
|
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: 0.9770114942528736 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# rmsProps_VitB-p32-384-1e-4-batch_32_epoch_4_classes_24 |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch32-384](https://huggingface.co/google/vit-base-patch32-384) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0970 |
|
- Accuracy: 0.9770 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 4 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.0292 | 0.14 | 100 | 0.1481 | 0.9655 | |
|
| 0.0026 | 0.28 | 200 | 0.1295 | 0.9741 | |
|
| 0.043 | 0.42 | 300 | 0.1905 | 0.9641 | |
|
| 0.0099 | 0.56 | 400 | 0.2070 | 0.9641 | |
|
| 0.0028 | 0.7 | 500 | 0.1291 | 0.9727 | |
|
| 0.0206 | 0.84 | 600 | 0.1674 | 0.9612 | |
|
| 0.0007 | 0.97 | 700 | 0.1307 | 0.9684 | |
|
| 0.0004 | 1.11 | 800 | 0.1403 | 0.9698 | |
|
| 0.0564 | 1.25 | 900 | 0.1523 | 0.9670 | |
|
| 0.0247 | 1.39 | 1000 | 0.2492 | 0.9397 | |
|
| 0.0005 | 1.53 | 1100 | 0.1087 | 0.9799 | |
|
| 0.0172 | 1.67 | 1200 | 0.1220 | 0.9741 | |
|
| 0.0073 | 1.81 | 1300 | 0.1126 | 0.9770 | |
|
| 0.0009 | 1.95 | 1400 | 0.1326 | 0.9727 | |
|
| 0.0101 | 2.09 | 1500 | 0.1339 | 0.9713 | |
|
| 0.0018 | 2.23 | 1600 | 0.1344 | 0.9698 | |
|
| 0.0002 | 2.37 | 1700 | 0.1588 | 0.9713 | |
|
| 0.0147 | 2.51 | 1800 | 0.1543 | 0.9698 | |
|
| 0.0292 | 2.65 | 1900 | 0.1266 | 0.9770 | |
|
| 0.0001 | 2.79 | 2000 | 0.1535 | 0.9727 | |
|
| 0.0 | 2.92 | 2100 | 0.1384 | 0.9756 | |
|
| 0.0023 | 3.06 | 2200 | 0.1438 | 0.9713 | |
|
| 0.0001 | 3.2 | 2300 | 0.1258 | 0.9741 | |
|
| 0.0 | 3.34 | 2400 | 0.1038 | 0.9770 | |
|
| 0.0001 | 3.48 | 2500 | 0.1010 | 0.9756 | |
|
| 0.0001 | 3.62 | 2600 | 0.1007 | 0.9770 | |
|
| 0.0 | 3.76 | 2700 | 0.1002 | 0.9770 | |
|
| 0.0 | 3.9 | 2800 | 0.0970 | 0.9770 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
