metadata
license: apache-2.0
base_model: microsoft/beit-base-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: smids_3x_beit_base_sgd_001_fold5
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.38166666666666665
smids_3x_beit_base_sgd_001_fold5
This model is a fine-tuned version of microsoft/beit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.1851
- Accuracy: 0.3817
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2835 | 1.0 | 225 | 1.3130 | 0.3167 |
| 1.3011 | 2.0 | 450 | 1.3069 | 0.3167 |
| 1.243 | 3.0 | 675 | 1.3010 | 0.3217 |
| 1.2411 | 4.0 | 900 | 1.2953 | 0.325 |
| 1.2229 | 5.0 | 1125 | 1.2898 | 0.3233 |
| 1.2191 | 6.0 | 1350 | 1.2846 | 0.3233 |
| 1.2208 | 7.0 | 1575 | 1.2796 | 0.3233 |
| 1.1965 | 8.0 | 1800 | 1.2748 | 0.3283 |
| 1.2527 | 9.0 | 2025 | 1.2700 | 0.3333 |
| 1.2362 | 10.0 | 2250 | 1.2655 | 0.335 |
| 1.2197 | 11.0 | 2475 | 1.2613 | 0.335 |
| 1.2149 | 12.0 | 2700 | 1.2570 | 0.34 |
| 1.2002 | 13.0 | 2925 | 1.2530 | 0.3433 |
| 1.1732 | 14.0 | 3150 | 1.2491 | 0.3483 |
| 1.2252 | 15.0 | 3375 | 1.2454 | 0.35 |
| 1.1628 | 16.0 | 3600 | 1.2417 | 0.3533 |
| 1.1999 | 17.0 | 3825 | 1.2381 | 0.3583 |
| 1.1844 | 18.0 | 4050 | 1.2348 | 0.3617 |
| 1.1674 | 19.0 | 4275 | 1.2315 | 0.3617 |
| 1.2258 | 20.0 | 4500 | 1.2284 | 0.36 |
| 1.1214 | 21.0 | 4725 | 1.2254 | 0.3633 |
| 1.151 | 22.0 | 4950 | 1.2225 | 0.365 |
| 1.1693 | 23.0 | 5175 | 1.2197 | 0.3667 |
| 1.1675 | 24.0 | 5400 | 1.2170 | 0.3667 |
| 1.1534 | 25.0 | 5625 | 1.2144 | 0.3667 |
| 1.1654 | 26.0 | 5850 | 1.2120 | 0.3667 |
| 1.1707 | 27.0 | 6075 | 1.2097 | 0.3683 |
| 1.1315 | 28.0 | 6300 | 1.2075 | 0.3683 |
| 1.1501 | 29.0 | 6525 | 1.2054 | 0.37 |
| 1.1251 | 30.0 | 6750 | 1.2034 | 0.37 |
| 1.2017 | 31.0 | 6975 | 1.2016 | 0.3717 |
| 1.0794 | 32.0 | 7200 | 1.1998 | 0.3717 |
| 1.1172 | 33.0 | 7425 | 1.1981 | 0.3767 |
| 1.1136 | 34.0 | 7650 | 1.1965 | 0.38 |
| 1.1368 | 35.0 | 7875 | 1.1951 | 0.3817 |
| 1.1416 | 36.0 | 8100 | 1.1937 | 0.38 |
| 1.0723 | 37.0 | 8325 | 1.1925 | 0.3833 |
| 1.0984 | 38.0 | 8550 | 1.1914 | 0.3833 |
| 1.0812 | 39.0 | 8775 | 1.1903 | 0.3817 |
| 1.1275 | 40.0 | 9000 | 1.1894 | 0.3817 |
| 1.1166 | 41.0 | 9225 | 1.1885 | 0.3817 |
| 1.1269 | 42.0 | 9450 | 1.1878 | 0.3817 |
| 1.1329 | 43.0 | 9675 | 1.1871 | 0.3817 |
| 1.1408 | 44.0 | 9900 | 1.1865 | 0.3817 |
| 1.1416 | 45.0 | 10125 | 1.1861 | 0.3817 |
| 1.1445 | 46.0 | 10350 | 1.1857 | 0.3817 |
| 1.1225 | 47.0 | 10575 | 1.1854 | 0.3817 |
| 1.1385 | 48.0 | 10800 | 1.1852 | 0.3817 |
| 1.1537 | 49.0 | 11025 | 1.1851 | 0.3817 |
| 1.1246 | 50.0 | 11250 | 1.1851 | 0.3817 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2