|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
model-index: |
|
- name: ViT_Flower102_4 |
|
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. --> |
|
|
|
# ViT_Flower102_4 |
|
|
|
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: 0.1042 |
|
- Accuracy: 0.9814 |
|
- Precision: 0.9814 |
|
- Recall: 0.9814 |
|
- F1: 0.9814 |
|
|
|
## 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: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
| 0.006 | 0.22 | 100 | 0.0735 | 0.9863 | 0.9863 | 0.9863 | 0.9863 | |
|
| 0.0044 | 0.45 | 200 | 0.0720 | 0.9882 | 0.9882 | 0.9882 | 0.9882 | |
|
| 0.3589 | 0.67 | 300 | 0.5454 | 0.8902 | 0.8902 | 0.8902 | 0.8902 | |
|
| 0.401 | 0.89 | 400 | 0.6406 | 0.8676 | 0.8676 | 0.8676 | 0.8676 | |
|
| 0.1851 | 1.11 | 500 | 0.4838 | 0.8912 | 0.8912 | 0.8912 | 0.8912 | |
|
| 0.1116 | 1.34 | 600 | 0.3375 | 0.9245 | 0.9245 | 0.9245 | 0.9245 | |
|
| 0.2359 | 1.56 | 700 | 0.4032 | 0.9059 | 0.9059 | 0.9059 | 0.9059 | |
|
| 0.062 | 1.78 | 800 | 0.2356 | 0.9549 | 0.9549 | 0.9549 | 0.9549 | |
|
| 0.0221 | 2.0 | 900 | 0.2307 | 0.9559 | 0.9559 | 0.9559 | 0.9559 | |
|
| 0.0052 | 2.23 | 1000 | 0.1620 | 0.9676 | 0.9676 | 0.9676 | 0.9676 | |
|
| 0.0277 | 2.45 | 1100 | 0.1881 | 0.9676 | 0.9676 | 0.9676 | 0.9676 | |
|
| 0.0025 | 2.67 | 1200 | 0.1483 | 0.9735 | 0.9735 | 0.9735 | 0.9735 | |
|
| 0.0078 | 2.9 | 1300 | 0.1199 | 0.9794 | 0.9794 | 0.9794 | 0.9794 | |
|
| 0.002 | 3.12 | 1400 | 0.1343 | 0.9755 | 0.9755 | 0.9755 | 0.9755 | |
|
| 0.0035 | 3.34 | 1500 | 0.1247 | 0.9775 | 0.9775 | 0.9775 | 0.9775 | |
|
| 0.0245 | 3.56 | 1600 | 0.1116 | 0.9775 | 0.9775 | 0.9775 | 0.9775 | |
|
| 0.0015 | 3.79 | 1700 | 0.1099 | 0.9775 | 0.9775 | 0.9775 | 0.9775 | |
|
| 0.0013 | 4.01 | 1800 | 0.1089 | 0.9804 | 0.9804 | 0.9804 | 0.9804 | |
|
| 0.0014 | 4.23 | 1900 | 0.1081 | 0.9804 | 0.9804 | 0.9804 | 0.9804 | |
|
| 0.0013 | 4.45 | 2000 | 0.1076 | 0.9804 | 0.9804 | 0.9804 | 0.9804 | |
|
| 0.0012 | 4.68 | 2100 | 0.1075 | 0.9804 | 0.9804 | 0.9804 | 0.9804 | |
|
| 0.0013 | 4.9 | 2200 | 0.1042 | 0.9814 | 0.9814 | 0.9814 | 0.9814 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|