|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- image-classification |
|
- generated_from_trainer |
|
model-index: |
|
- name: ryan_model3272024 |
|
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_model3272024 |
|
|
|
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 properties dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2636 |
|
- Ordinal Mae: 0.5544 |
|
- Ordinal Accuracy: 0.5810 |
|
- Na Accuracy: 0.7915 |
|
|
|
## 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 | Ordinal Mae | Ordinal Accuracy | Na Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:-----------:|:----------------:|:-----------:| |
|
| 0.3524 | 0.05 | 100 | 0.3400 | 0.8905 | 0.3875 | 0.7587 | |
|
| 0.2683 | 0.09 | 200 | 0.3671 | 0.7306 | 0.4892 | 0.6236 | |
|
| 0.3314 | 0.14 | 300 | 0.3450 | 0.8077 | 0.4013 | 0.6969 | |
|
| 0.2747 | 0.19 | 400 | 0.2813 | 0.6106 | 0.5423 | 0.7896 | |
|
| 0.3247 | 0.23 | 500 | 0.3144 | 0.7256 | 0.4525 | 0.7104 | |
|
| 0.3612 | 0.28 | 600 | 0.3075 | 0.6416 | 0.4984 | 0.7587 | |
|
| 0.3031 | 0.32 | 700 | 0.2785 | 0.5720 | 0.5556 | 0.7896 | |
|
| 0.2866 | 0.37 | 800 | 0.2878 | 0.5348 | 0.5776 | 0.7336 | |
|
| 0.2927 | 0.42 | 900 | 0.2689 | 0.5855 | 0.5574 | 0.7973 | |
|
| 0.3003 | 0.46 | 1000 | 0.2636 | 0.5544 | 0.5810 | 0.7915 | |
|
| 0.2522 | 0.51 | 1100 | 0.3009 | 0.5651 | 0.5444 | 0.8571 | |
|
| 0.262 | 0.56 | 1200 | 0.2790 | 0.5203 | 0.5802 | 0.8301 | |
|
| 0.2139 | 0.6 | 1300 | 0.2653 | 0.5626 | 0.5493 | 0.7510 | |
|
| 0.2655 | 0.65 | 1400 | 0.2760 | 0.6107 | 0.5426 | 0.7124 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.1 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
