|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- image-classification |
|
- generated_from_trainer |
|
model-index: |
|
- name: ryan_model314 |
|
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. --> |
|
|
|
# ryan_model314 |
|
|
|
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: 0.2532 |
|
- Na Accuracy: 0.947 |
|
- Ordinal Accuracy: 0.5952 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 4 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Na Accuracy | Ordinal Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:-----------:|:----------------:| |
|
| 0.3042 | 0.16 | 100 | 0.3673 | 0.928 | 0.4671 | |
|
| 0.2904 | 0.32 | 200 | 0.2977 | 0.933 | 0.5790 | |
|
| 0.2648 | 0.48 | 300 | 0.2831 | 0.944 | 0.5940 | |
|
| 0.3036 | 0.64 | 400 | 0.2776 | 0.949 | 0.5871 | |
|
| 0.2656 | 0.8 | 500 | 0.2846 | 0.931 | 0.6101 | |
|
| 0.2954 | 0.96 | 600 | 0.2532 | 0.947 | 0.5952 | |
|
| 0.1991 | 1.12 | 700 | 0.2603 | 0.942 | 0.6078 | |
|
| 0.1678 | 1.28 | 800 | 0.2905 | 0.942 | 0.6332 | |
|
| 0.2514 | 1.44 | 900 | 0.2566 | 0.94 | 0.6090 | |
|
| 0.2328 | 1.6 | 1000 | 0.2884 | 0.94 | 0.5617 | |
|
| 0.1826 | 1.76 | 1100 | 0.2870 | 0.943 | 0.6044 | |
|
| 0.2013 | 1.92 | 1200 | 0.2937 | 0.941 | 0.5905 | |
|
| 0.0663 | 2.08 | 1300 | 0.2954 | 0.938 | 0.6251 | |
|
| 0.1503 | 2.24 | 1400 | 0.3188 | 0.937 | 0.5986 | |
|
| 0.0611 | 2.4 | 1500 | 0.3393 | 0.945 | 0.5998 | |
|
| 0.0743 | 2.56 | 1600 | 0.3182 | 0.942 | 0.6482 | |
|
| 0.0908 | 2.72 | 1700 | 0.3332 | 0.942 | 0.6482 | |
|
| 0.1108 | 2.88 | 1800 | 0.3256 | 0.943 | 0.6459 | |
|
| 0.0786 | 3.04 | 1900 | 0.3222 | 0.944 | 0.6540 | |
|
| 0.043 | 3.2 | 2000 | 0.3501 | 0.941 | 0.6482 | |
|
| 0.0472 | 3.36 | 2100 | 0.3455 | 0.943 | 0.6609 | |
|
| 0.032 | 3.52 | 2200 | 0.3562 | 0.94 | 0.6517 | |
|
| 0.0434 | 3.68 | 2300 | 0.3499 | 0.94 | 0.6597 | |
|
| 0.0341 | 3.84 | 2400 | 0.3611 | 0.94 | 0.6482 | |
|
| 0.0305 | 4.0 | 2500 | 0.3635 | 0.939 | 0.6609 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.1 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|