---
base_model: openai/clip-vit-base-patch32
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: document-spoof-clip
  results:
  - task:
      name: Image Classification
      type: image-classification
    dataset:
      name: imagefolder
      type: imagefolder
      config: default
      split: validation
      args: default
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.9857142857142858
---

<!-- 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. -->

# document-spoof-clip

This model is a fine-tuned version of [openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1338
- Accuracy: 0.9857

## 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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Accuracy |
|:-------------:|:-------:|:----:|:---------------:|:--------:|
| No log        | 0.8421  | 4    | 0.6403          | 0.6571   |
| No log        | 1.8947  | 9    | 0.9389          | 0.6714   |
| 0.572         | 2.9474  | 14   | 0.2936          | 0.8857   |
| 0.572         | 4.0     | 19   | 0.6845          | 0.8143   |
| 0.4928        | 4.8421  | 23   | 0.0334          | 0.9857   |
| 0.4928        | 5.8947  | 28   | 0.1273          | 0.9571   |
| 0.0987        | 6.9474  | 33   | 0.0738          | 0.9857   |
| 0.0987        | 8.0     | 38   | 0.1519          | 0.9571   |
| 0.017         | 8.8421  | 42   | 0.0569          | 0.9714   |
| 0.017         | 9.8947  | 47   | 0.1164          | 0.9857   |
| 0.0062        | 10.9474 | 52   | 0.0672          | 0.9714   |
| 0.0062        | 12.0    | 57   | 0.0446          | 0.9714   |
| 0.0084        | 12.8421 | 61   | 0.0882          | 0.9857   |
| 0.0084        | 13.8947 | 66   | 0.1117          | 0.9714   |
| 0.0           | 14.9474 | 71   | 0.1420          | 0.9714   |
| 0.0           | 16.0    | 76   | 0.1360          | 0.9714   |
| 0.0001        | 16.8421 | 80   | 0.1338          | 0.9857   |


### Framework versions

- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1