|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- image-classification |
|
- generated_from_trainer |
|
model-index: |
|
- name: ryan_model314_3 |
|
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_3 |
|
|
|
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: 0.2547 |
|
- Na Accuracy: 0.95 |
|
- Ordinal Mae: 1.2090 |
|
|
|
## 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: 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 Mae | |
|
|:-------------:|:-----:|:----:|:---------------:|:-----------:|:-----------:| |
|
| 0.4505 | 0.2 | 25 | 0.4262 | 0.9 | 1.0092 | |
|
| 0.3847 | 0.4 | 50 | 0.3676 | 0.935 | 1.3719 | |
|
| 0.3061 | 0.6 | 75 | 0.3262 | 0.945 | 0.7486 | |
|
| 0.2744 | 0.8 | 100 | 0.3524 | 0.905 | 1.1408 | |
|
| 0.2384 | 1.0 | 125 | 0.3611 | 0.93 | 0.6747 | |
|
| 0.2021 | 1.2 | 150 | 0.3105 | 0.95 | 1.0441 | |
|
| 0.2234 | 1.4 | 175 | 0.2738 | 0.955 | 1.4168 | |
|
| 0.187 | 1.6 | 200 | 0.2688 | 0.955 | 1.3653 | |
|
| 0.2008 | 1.8 | 225 | 0.2669 | 0.96 | 0.8936 | |
|
| 0.1541 | 2.0 | 250 | 0.2547 | 0.95 | 1.2090 | |
|
| 0.1201 | 2.2 | 275 | 0.2725 | 0.95 | 0.7955 | |
|
| 0.113 | 2.4 | 300 | 0.2818 | 0.955 | 1.2378 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.1 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
