|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch32-224-in21k |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: rmsProp_ViTB-32-224-in21k-1e-4-batch_16_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: 0.9583333333333334 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# rmsProp_ViTB-32-224-in21k-1e-4-batch_16_epoch_4_classes_24 |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch32-224-in21k](https://huggingface.co/google/vit-base-patch32-224-in21k) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1773 |
|
- Accuracy: 0.9583 |
|
|
|
## 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: 16 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.5163 | 0.07 | 100 | 1.4460 | 0.8779 | |
|
| 0.7184 | 0.14 | 200 | 0.8418 | 0.8764 | |
|
| 0.3902 | 0.21 | 300 | 0.5001 | 0.9066 | |
|
| 0.3509 | 0.28 | 400 | 0.4132 | 0.9138 | |
|
| 0.1873 | 0.35 | 500 | 0.3207 | 0.9282 | |
|
| 0.2124 | 0.42 | 600 | 0.3325 | 0.9239 | |
|
| 0.1122 | 0.49 | 700 | 0.2961 | 0.9267 | |
|
| 0.135 | 0.56 | 800 | 0.2646 | 0.9353 | |
|
| 0.1275 | 0.63 | 900 | 0.2384 | 0.9411 | |
|
| 0.1194 | 0.7 | 1000 | 0.2189 | 0.9397 | |
|
| 0.1968 | 0.77 | 1100 | 0.2539 | 0.9282 | |
|
| 0.078 | 0.84 | 1200 | 0.2293 | 0.9353 | |
|
| 0.0345 | 0.91 | 1300 | 0.1585 | 0.9626 | |
|
| 0.1068 | 0.97 | 1400 | 0.2896 | 0.9181 | |
|
| 0.0429 | 1.04 | 1500 | 0.1876 | 0.9497 | |
|
| 0.0153 | 1.11 | 1600 | 0.2637 | 0.9296 | |
|
| 0.0296 | 1.18 | 1700 | 0.2153 | 0.9454 | |
|
| 0.0262 | 1.25 | 1800 | 0.2906 | 0.9339 | |
|
| 0.023 | 1.32 | 1900 | 0.2271 | 0.9483 | |
|
| 0.0154 | 1.39 | 2000 | 0.2772 | 0.9397 | |
|
| 0.0778 | 1.46 | 2100 | 0.2510 | 0.9353 | |
|
| 0.0504 | 1.53 | 2200 | 0.1866 | 0.9555 | |
|
| 0.0563 | 1.6 | 2300 | 0.2228 | 0.9454 | |
|
| 0.0481 | 1.67 | 2400 | 0.2390 | 0.9497 | |
|
| 0.0602 | 1.74 | 2500 | 0.2601 | 0.9382 | |
|
| 0.0253 | 1.81 | 2600 | 0.2905 | 0.9339 | |
|
| 0.0433 | 1.88 | 2700 | 0.2805 | 0.9325 | |
|
| 0.0039 | 1.95 | 2800 | 0.2264 | 0.9425 | |
|
| 0.0476 | 2.02 | 2900 | 0.2195 | 0.9511 | |
|
| 0.0036 | 2.09 | 3000 | 0.2174 | 0.9511 | |
|
| 0.003 | 2.16 | 3100 | 0.1697 | 0.9583 | |
|
| 0.0026 | 2.23 | 3200 | 0.2194 | 0.9555 | |
|
| 0.0049 | 2.3 | 3300 | 0.2416 | 0.9468 | |
|
| 0.0023 | 2.37 | 3400 | 0.1703 | 0.9612 | |
|
| 0.0023 | 2.44 | 3500 | 0.2082 | 0.9583 | |
|
| 0.0262 | 2.51 | 3600 | 0.2328 | 0.9468 | |
|
| 0.0026 | 2.58 | 3700 | 0.1798 | 0.9583 | |
|
| 0.0458 | 2.65 | 3800 | 0.2406 | 0.9483 | |
|
| 0.0027 | 2.72 | 3900 | 0.2298 | 0.9511 | |
|
| 0.0019 | 2.79 | 4000 | 0.1836 | 0.9598 | |
|
| 0.0146 | 2.86 | 4100 | 0.2025 | 0.9526 | |
|
| 0.0739 | 2.92 | 4200 | 0.1946 | 0.9598 | |
|
| 0.0054 | 2.99 | 4300 | 0.1972 | 0.9569 | |
|
| 0.0015 | 3.06 | 4400 | 0.2329 | 0.9511 | |
|
| 0.0015 | 3.13 | 4500 | 0.2094 | 0.9569 | |
|
| 0.0016 | 3.2 | 4600 | 0.1888 | 0.9598 | |
|
| 0.0017 | 3.27 | 4700 | 0.1853 | 0.9569 | |
|
| 0.0014 | 3.34 | 4800 | 0.1809 | 0.9612 | |
|
| 0.0013 | 3.41 | 4900 | 0.1802 | 0.9583 | |
|
| 0.0014 | 3.48 | 5000 | 0.1795 | 0.9569 | |
|
| 0.0012 | 3.55 | 5100 | 0.1737 | 0.9583 | |
|
| 0.0012 | 3.62 | 5200 | 0.1777 | 0.9569 | |
|
| 0.0012 | 3.69 | 5300 | 0.1796 | 0.9555 | |
|
| 0.0012 | 3.76 | 5400 | 0.1782 | 0.9569 | |
|
| 0.0012 | 3.83 | 5500 | 0.1771 | 0.9583 | |
|
| 0.0012 | 3.9 | 5600 | 0.1773 | 0.9583 | |
|
| 0.0011 | 3.97 | 5700 | 0.1773 | 0.9583 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
