|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
base_model: google/vit-base-patch16-224-in21k |
|
model-index: |
|
- name: snacks_classification |
|
results: [] |
|
datasets: |
|
- Matthijs/snacks |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# snacks_classification |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4458 |
|
- Accuracy: 0.8942 |
|
|
|
## 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: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 13 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 1.0 | 303 | 0.7200 | 0.8649 | |
|
| 1.0168 | 2.0 | 606 | 0.5468 | 0.8723 | |
|
| 1.0168 | 3.0 | 909 | 0.4612 | 0.8848 | |
|
| 0.3765 | 4.0 | 1212 | 0.5239 | 0.8660 | |
|
| 0.2585 | 5.0 | 1515 | 0.4193 | 0.8890 | |
|
| 0.2585 | 6.0 | 1818 | 0.4571 | 0.8775 | |
|
| 0.2038 | 7.0 | 2121 | 0.4538 | 0.8838 | |
|
| 0.2038 | 8.0 | 2424 | 0.4508 | 0.8880 | |
|
| 0.1827 | 9.0 | 2727 | 0.4748 | 0.8880 | |
|
| 0.1568 | 10.0 | 3030 | 0.4928 | 0.8764 | |
|
| 0.1568 | 11.0 | 3333 | 0.3684 | 0.9099 | |
|
| 0.1305 | 12.0 | 3636 | 0.4205 | 0.8984 | |
|
| 0.1305 | 13.0 | 3939 | 0.4537 | 0.8963 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.17.1 |
|
- Tokenizers 0.15.2 |
