---
license: apache-2.0
base_model: jordyvl/vit-base_rvl-cdip
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vit-base_rvl_cdip-N1K_AURC_128
  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-base_rvl_cdip-N1K_AURC_128

This model is a fine-tuned version of [jordyvl/vit-base_rvl-cdip](https://huggingface.co/jordyvl/vit-base_rvl-cdip) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2754
- Accuracy: 0.8962
- Brier Loss: 0.1742
- Nll: 0.8794
- F1 Micro: 0.8962
- F1 Macro: 0.8963
- Ece: 0.0736
- Aurc: 0.0200

## 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: 2e-05
- 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Brier Loss | Nll    | F1 Micro | F1 Macro | Ece    | Aurc   |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:----------:|:------:|:--------:|:--------:|:------:|:------:|
| No log        | 1.0   | 125  | 0.1357          | 0.8898   | 0.1657     | 1.2064 | 0.8898   | 0.8907   | 0.0492 | 0.0181 |
| No log        | 2.0   | 250  | 0.1615          | 0.898    | 0.1602     | 1.0955 | 0.898    | 0.8986   | 0.0473 | 0.0181 |
| No log        | 3.0   | 375  | 0.1795          | 0.896    | 0.1630     | 1.0031 | 0.8960   | 0.8959   | 0.0599 | 0.0180 |
| 0.0132        | 4.0   | 500  | 0.2094          | 0.8978   | 0.1662     | 0.9561 | 0.8978   | 0.8977   | 0.0633 | 0.0187 |
| 0.0132        | 5.0   | 625  | 0.2290          | 0.898    | 0.1692     | 0.9249 | 0.898    | 0.8979   | 0.0665 | 0.0190 |
| 0.0132        | 6.0   | 750  | 0.2430          | 0.898    | 0.1714     | 0.9150 | 0.898    | 0.8981   | 0.0690 | 0.0194 |
| 0.0132        | 7.0   | 875  | 0.2567          | 0.898    | 0.1718     | 0.8888 | 0.898    | 0.8979   | 0.0702 | 0.0196 |
| 0.0022        | 8.0   | 1000 | 0.2740          | 0.8975   | 0.1734     | 0.8800 | 0.8975   | 0.8975   | 0.0718 | 0.0199 |
| 0.0022        | 9.0   | 1125 | 0.2715          | 0.896    | 0.1743     | 0.8824 | 0.8960   | 0.8960   | 0.0737 | 0.0199 |
| 0.0022        | 10.0  | 1250 | 0.2754          | 0.8962   | 0.1742     | 0.8794 | 0.8962   | 0.8963   | 0.0736 | 0.0200 |


### Framework versions

- Transformers 4.33.3
- Pytorch 2.2.0.dev20231002
- Datasets 2.7.1
- Tokenizers 0.13.3