|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- image-classification |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: id1 |
|
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. --> |
|
|
|
# id1 |
|
|
|
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 sooks/id1 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6181 |
|
- Accuracy: 0.6535 |
|
|
|
## 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: 6 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:------:|:---------------:|:--------:| |
|
| 0.6933 | 0.53 | 10000 | 0.6932 | 0.5008 | |
|
| 0.6933 | 1.06 | 20000 | 0.6933 | 0.4992 | |
|
| 0.6933 | 1.59 | 30000 | 0.6931 | 0.5008 | |
|
| 0.6933 | 2.12 | 40000 | 0.6931 | 0.5161 | |
|
| 0.6931 | 2.65 | 50000 | 0.6933 | 0.4991 | |
|
| 0.6932 | 3.19 | 60000 | 0.6932 | 0.4991 | |
|
| 0.6746 | 3.72 | 70000 | 0.6725 | 0.5796 | |
|
| 0.6582 | 4.25 | 80000 | 0.6614 | 0.6032 | |
|
| 0.6455 | 4.78 | 90000 | 0.6466 | 0.6132 | |
|
| 0.6256 | 5.31 | 100000 | 0.6325 | 0.6391 | |
|
| 0.6144 | 5.84 | 110000 | 0.6181 | 0.6535 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
