|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- image-classification |
|
- vision |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: food101-vit-base-patch16-224-in21k |
|
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. --> |
|
|
|
# food101-vit-base-patch16-224-in21k |
|
|
|
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 food101 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3853 |
|
- Accuracy: 0.908 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 1337 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
| 0.8312 | 1.0 | 9469 | 0.6893 | 0.8576 | |
|
| 0.6401 | 2.0 | 18938 | 0.4571 | 0.8784 | |
|
| 0.7021 | 3.0 | 28407 | 0.4081 | 0.8905 | |
|
| 0.8365 | 4.0 | 37876 | 0.3962 | 0.8946 | |
|
| 0.3562 | 5.0 | 47345 | 0.3932 | 0.8954 | |
|
| 0.3552 | 6.0 | 56814 | 0.3876 | 0.9004 | |
|
| 0.3962 | 7.0 | 66283 | 0.3854 | 0.9049 | |
|
| 0.4242 | 8.0 | 75752 | 0.3865 | 0.9066 | |
|
| 0.2785 | 9.0 | 85221 | 0.3867 | 0.9070 | |
|
| 0.3446 | 10.0 | 94690 | 0.3853 | 0.908 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.0 |
|
- Pytorch 2.1.2+cu118 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.15.2 |
|
|
