|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-large-patch16-384 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: vitLarge-16-384-2e-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: 0.9712643678160919 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# vitLarge-16-384-2e-4-batch_16_epoch_4_classes_24 |
|
|
|
This model is a fine-tuned version of [google/vit-large-patch16-384](https://huggingface.co/google/vit-large-patch16-384) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1519 |
|
- Accuracy: 0.9713 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.7944 | 0.03 | 100 | 0.8483 | 0.7428 | |
|
| 1.1261 | 0.07 | 200 | 1.0595 | 0.6911 | |
|
| 0.7575 | 0.1 | 300 | 0.5007 | 0.8534 | |
|
| 0.3567 | 0.14 | 400 | 0.5404 | 0.8391 | |
|
| 0.4062 | 0.17 | 500 | 0.7795 | 0.7974 | |
|
| 0.4227 | 0.21 | 600 | 0.3598 | 0.8851 | |
|
| 0.3436 | 0.24 | 700 | 0.4550 | 0.8693 | |
|
| 0.7695 | 0.28 | 800 | 0.5748 | 0.8247 | |
|
| 0.2864 | 0.31 | 900 | 0.4017 | 0.8793 | |
|
| 0.3718 | 0.35 | 1000 | 0.5384 | 0.8420 | |
|
| 0.2764 | 0.38 | 1100 | 0.4682 | 0.8764 | |
|
| 0.3438 | 0.42 | 1200 | 0.4194 | 0.8807 | |
|
| 0.4031 | 0.45 | 1300 | 0.4105 | 0.8922 | |
|
| 0.449 | 0.49 | 1400 | 0.4499 | 0.8678 | |
|
| 0.2249 | 0.52 | 1500 | 0.2701 | 0.9066 | |
|
| 0.2398 | 0.56 | 1600 | 0.4124 | 0.8807 | |
|
| 0.5759 | 0.59 | 1700 | 0.8378 | 0.7960 | |
|
| 0.1315 | 0.63 | 1800 | 0.4757 | 0.8779 | |
|
| 0.4481 | 0.66 | 1900 | 0.3463 | 0.9037 | |
|
| 0.2183 | 0.7 | 2000 | 0.4291 | 0.8779 | |
|
| 0.2101 | 0.73 | 2100 | 0.3318 | 0.9109 | |
|
| 1.0071 | 0.77 | 2200 | 2.9399 | 0.2098 | |
|
| 0.3426 | 0.8 | 2300 | 0.4231 | 0.9023 | |
|
| 0.1126 | 0.84 | 2400 | 0.3609 | 0.9124 | |
|
| 0.3954 | 0.87 | 2500 | 0.4471 | 0.8994 | |
|
| 0.2099 | 0.91 | 2600 | 0.3465 | 0.9052 | |
|
| 0.1982 | 0.94 | 2700 | 0.4135 | 0.8994 | |
|
| 0.1931 | 0.98 | 2800 | 0.3306 | 0.9095 | |
|
| 0.1721 | 1.01 | 2900 | 0.3470 | 0.9195 | |
|
| 0.1864 | 1.04 | 3000 | 0.3814 | 0.9124 | |
|
| 0.0652 | 1.08 | 3100 | 0.2534 | 0.9296 | |
|
| 0.1176 | 1.11 | 3200 | 0.2744 | 0.9210 | |
|
| 0.0988 | 1.15 | 3300 | 0.2966 | 0.9325 | |
|
| 0.0289 | 1.18 | 3400 | 0.2021 | 0.9555 | |
|
| 0.1465 | 1.22 | 3500 | 0.1566 | 0.9583 | |
|
| 0.2023 | 1.25 | 3600 | 0.2803 | 0.9353 | |
|
| 0.1042 | 1.29 | 3700 | 0.2893 | 0.9282 | |
|
| 0.1403 | 1.32 | 3800 | 0.3145 | 0.9239 | |
|
| 0.0786 | 1.36 | 3900 | 0.3188 | 0.9267 | |
|
| 0.2427 | 1.39 | 4000 | 0.6615 | 0.8693 | |
|
| 0.3187 | 1.43 | 4100 | 0.3598 | 0.9195 | |
|
| 0.0897 | 1.46 | 4200 | 0.2778 | 0.9425 | |
|
| 0.068 | 1.5 | 4300 | 0.3445 | 0.9124 | |
|
| 0.2165 | 1.53 | 4400 | 0.2351 | 0.9468 | |
|
| 0.0807 | 1.57 | 4500 | 0.3111 | 0.9310 | |
|
| 0.007 | 1.6 | 4600 | 0.2208 | 0.9483 | |
|
| 0.0017 | 1.64 | 4700 | 0.1943 | 0.9411 | |
|
| 0.081 | 1.67 | 4800 | 0.3503 | 0.9239 | |
|
| 0.0285 | 1.71 | 4900 | 0.3109 | 0.9239 | |
|
| 0.0495 | 1.74 | 5000 | 0.1233 | 0.9641 | |
|
| 0.0201 | 1.78 | 5100 | 0.2508 | 0.9483 | |
|
| 0.1186 | 1.81 | 5200 | 0.3854 | 0.9210 | |
|
| 0.0283 | 1.85 | 5300 | 0.2336 | 0.9425 | |
|
| 0.0569 | 1.88 | 5400 | 0.2872 | 0.9425 | |
|
| 0.0498 | 1.92 | 5500 | 0.2462 | 0.9569 | |
|
| 0.0101 | 1.95 | 5600 | 0.2256 | 0.9511 | |
|
| 0.0474 | 1.99 | 5700 | 0.2201 | 0.9569 | |
|
| 0.0008 | 2.02 | 5800 | 0.2079 | 0.9526 | |
|
| 0.0 | 2.06 | 5900 | 0.1951 | 0.9583 | |
|
| 0.0007 | 2.09 | 6000 | 0.1449 | 0.9626 | |
|
| 0.003 | 2.12 | 6100 | 0.1411 | 0.9670 | |
|
| 0.0028 | 2.16 | 6200 | 0.1889 | 0.9598 | |
|
| 0.0018 | 2.19 | 6300 | 0.2356 | 0.9511 | |
|
| 0.0087 | 2.23 | 6400 | 0.2185 | 0.9569 | |
|
| 0.0169 | 2.26 | 6500 | 0.1898 | 0.9583 | |
|
| 0.0003 | 2.3 | 6600 | 0.1879 | 0.9655 | |
|
| 0.0008 | 2.33 | 6700 | 0.1331 | 0.9713 | |
|
| 0.0001 | 2.37 | 6800 | 0.1537 | 0.9655 | |
|
| 0.0002 | 2.4 | 6900 | 0.2148 | 0.9598 | |
|
| 0.0079 | 2.44 | 7000 | 0.1258 | 0.9698 | |
|
| 0.0004 | 2.47 | 7100 | 0.1557 | 0.9698 | |
|
| 0.0 | 2.51 | 7200 | 0.1376 | 0.9698 | |
|
| 0.0007 | 2.54 | 7300 | 0.1238 | 0.9713 | |
|
| 0.0 | 2.58 | 7400 | 0.1433 | 0.9670 | |
|
| 0.0023 | 2.61 | 7500 | 0.1537 | 0.9684 | |
|
| 0.0004 | 2.65 | 7600 | 0.1302 | 0.9727 | |
|
| 0.0002 | 2.68 | 7700 | 0.1557 | 0.9698 | |
|
| 0.0013 | 2.72 | 7800 | 0.1614 | 0.9698 | |
|
| 0.0 | 2.75 | 7900 | 0.1713 | 0.9670 | |
|
| 0.0 | 2.79 | 8000 | 0.1458 | 0.9698 | |
|
| 0.0 | 2.82 | 8100 | 0.1453 | 0.9698 | |
|
| 0.0 | 2.86 | 8200 | 0.1527 | 0.9670 | |
|
| 0.0 | 2.89 | 8300 | 0.1508 | 0.9698 | |
|
| 0.0001 | 2.93 | 8400 | 0.1544 | 0.9713 | |
|
| 0.0 | 2.96 | 8500 | 0.1506 | 0.9713 | |
|
| 0.0 | 3.0 | 8600 | 0.1519 | 0.9713 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
