|
--- |
|
license: apache-2.0 |
|
base_model: WinKawaks/vit-tiny-patch16-224 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
model-index: |
|
- name: KDRSSC_ViT2TinyViT |
|
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. --> |
|
|
|
# KDRSSC_ViT2TinyViT |
|
|
|
This model is a fine-tuned version of [WinKawaks/vit-tiny-patch16-224](https://huggingface.co/WinKawaks/vit-tiny-patch16-224) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4414 |
|
- Accuracy: 0.9381 |
|
- Precision: 0.9385 |
|
- Recall: 0.9385 |
|
- F1: 0.9382 |
|
|
|
## 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: 128 |
|
- eval_batch_size: 128 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
| 0.9089 | 1.0 | 148 | 0.5624 | 0.906 | 0.9072 | 0.9014 | 0.8987 | |
|
| 0.4816 | 2.0 | 296 | 0.4759 | 0.94 | 0.9411 | 0.9389 | 0.9382 | |
|
| 0.3958 | 3.0 | 444 | 0.4354 | 0.952 | 0.9503 | 0.9510 | 0.9496 | |
|
| 0.3574 | 4.0 | 592 | 0.4273 | 0.949 | 0.9475 | 0.9470 | 0.9460 | |
|
| 0.3406 | 5.0 | 740 | 0.4132 | 0.955 | 0.9548 | 0.9522 | 0.9523 | |
|
| 0.3341 | 6.0 | 888 | 0.4164 | 0.951 | 0.9481 | 0.9503 | 0.9477 | |
|
| 0.3314 | 7.0 | 1036 | 0.4087 | 0.957 | 0.9545 | 0.9538 | 0.9530 | |
|
| 0.3302 | 8.0 | 1184 | 0.4075 | 0.955 | 0.9528 | 0.9517 | 0.9512 | |
|
| 0.3295 | 9.0 | 1332 | 0.4067 | 0.956 | 0.9533 | 0.9533 | 0.9522 | |
|
| 0.3292 | 10.0 | 1480 | 0.4071 | 0.956 | 0.9534 | 0.9533 | 0.9522 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
