| --- |
| license: apache-2.0 |
| tags: |
| - image-classification |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| model-index: |
| - name: vit-base-clothing-leafs-example |
| results: [] |
| --- |
| |
| <!-- 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-clothing-leafs-example |
|
|
| This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the beans dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 6.1420 |
| - Accuracy: 0.0448 |
|
|
| ## 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: 0.0002 |
| - 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: 5 |
| - mixed_precision_training: Native AMP |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | |
| |:-------------:|:-----:|:-----:|:---------------:|:--------:| |
| | 8.6059 | 0.14 | 1000 | 8.5844 | 0.0002 | |
| | 8.5506 | 0.28 | 2000 | 8.5189 | 0.0010 | |
| | 8.4931 | 0.41 | 3000 | 8.4641 | 0.0012 | |
| | 8.4223 | 0.55 | 4000 | 8.3495 | 0.0016 | |
| | 8.3144 | 0.69 | 5000 | 8.2552 | 0.0021 | |
| | 8.1936 | 0.83 | 6000 | 8.1385 | 0.0024 | |
| | 8.0638 | 0.97 | 7000 | 7.9924 | 0.0028 | |
| | 7.8485 | 1.11 | 8000 | 7.8366 | 0.0036 | |
| | 7.6933 | 1.24 | 9000 | 7.6595 | 0.0045 | |
| | 7.5808 | 1.38 | 10000 | 7.5232 | 0.0062 | |
| | 7.4352 | 1.52 | 11000 | 7.3816 | 0.0070 | |
| | 7.3279 | 1.66 | 12000 | 7.2853 | 0.0084 | |
| | 7.2141 | 1.8 | 13000 | 7.1553 | 0.0105 | |
| | 7.151 | 1.94 | 14000 | 7.0853 | 0.0119 | |
| | 6.9695 | 2.07 | 15000 | 7.0088 | 0.0134 | |
| | 6.8563 | 2.21 | 16000 | 6.9409 | 0.0139 | |
| | 6.8019 | 2.35 | 17000 | 6.8634 | 0.0158 | |
| | 6.7372 | 2.49 | 18000 | 6.8001 | 0.0175 | |
| | 6.6903 | 2.63 | 19000 | 6.7323 | 0.0191 | |
| | 6.6482 | 2.77 | 20000 | 6.6638 | 0.0207 | |
| | 6.5669 | 2.9 | 21000 | 6.6090 | 0.0239 | |
| | 6.4484 | 3.04 | 22000 | 6.5441 | 0.0240 | |
| | 6.2568 | 3.18 | 23000 | 6.5015 | 0.0273 | |
| | 6.2452 | 3.32 | 24000 | 6.4589 | 0.0304 | |
| | 6.2002 | 3.46 | 25000 | 6.4312 | 0.0310 | |
| | 6.1699 | 3.6 | 26000 | 6.3723 | 0.0319 | |
| | 6.1284 | 3.73 | 27000 | 6.3324 | 0.0343 | |
| | 6.1186 | 3.87 | 28000 | 6.3029 | 0.0350 | |
| | 6.0611 | 4.01 | 29000 | 6.2723 | 0.0381 | |
| | 5.7883 | 4.15 | 30000 | 6.2527 | 0.0383 | |
| | 5.7684 | 4.29 | 31000 | 6.2186 | 0.0392 | |
| | 5.7701 | 4.43 | 32000 | 6.2031 | 0.0403 | |
| | 5.7473 | 4.56 | 33000 | 6.1777 | 0.0430 | |
| | 5.735 | 4.7 | 34000 | 6.1634 | 0.0442 | |
| | 5.7324 | 4.84 | 35000 | 6.1494 | 0.0443 | |
| | 5.6949 | 4.98 | 36000 | 6.1420 | 0.0448 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.29.2 |
| - Pytorch 2.0.1 |
| - Datasets 2.12.0 |
| - Tokenizers 0.13.3 |
|
|
