|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: finetuned-amazon |
|
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. --> |
|
|
|
# finetuned-amazon |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.7690 |
|
- Accuracy: 0.1038 |
|
- F1: 0.0409 |
|
|
|
## 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 | Accuracy | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 2.7793 | 0.27 | 100 | 2.7709 | 0.0390 | 0.0241 | |
|
| 2.773 | 0.54 | 200 | 2.7767 | 0.0410 | 0.0230 | |
|
| 2.7752 | 0.81 | 300 | 2.7872 | 0.0 | 0.0 | |
|
| 2.7731 | 1.08 | 400 | 2.7793 | 0.0171 | 0.0111 | |
|
| 2.7744 | 1.34 | 500 | 2.7733 | 0.0886 | 0.0507 | |
|
| 2.7755 | 1.61 | 600 | 2.7740 | 0.0733 | 0.0376 | |
|
| 2.7706 | 1.88 | 700 | 2.7755 | 0.0657 | 0.0401 | |
|
| 2.7723 | 2.15 | 800 | 2.7690 | 0.1038 | 0.0409 | |
|
| 2.7732 | 2.42 | 900 | 2.7738 | 0.1010 | 0.0410 | |
|
| 2.7738 | 2.69 | 1000 | 2.7729 | 0.0914 | 0.0384 | |
|
| 2.7734 | 2.96 | 1100 | 2.7732 | 0.0581 | 0.0343 | |
|
| 2.7723 | 3.23 | 1200 | 2.7726 | 0.0638 | 0.0361 | |
|
| 2.7725 | 3.49 | 1300 | 2.7731 | 0.0667 | 0.0297 | |
|
| 2.7725 | 3.76 | 1400 | 2.7734 | 0.0476 | 0.0296 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
