---
tags:
  - image-to-text
  - image-captioning
license: apache-2.0
metrics:
  - rouge
datasets:
  - Mozilla/flickr30k-transformed-captions-gpt4o
widget:
  - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/savanna.jpg
    example_title: Savanna
  - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/football-match.jpg
    example_title: Football Match
  - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/airport.jpg
    example_title: Airport
base_model:
  - google/vit-base-patch16-224-in21k
---

# distilvit

This model is a work in progress. Fine-tuned version of those base models:

- a VIT model for the image encoder: https://huggingface.co/google/vit-base-patch16-224-in21k
- a Distilled GPT-2 model for the text decoder: https://huggingface.co/distilbert/distilgpt2

This model was trained on:

- [Flickr30k debiased](https://huggingface.co/datasets/Mozilla/flickr30k-transformed-captions-gpt4o)
- [DocOrNot](https://huggingface.co/datasets/Mozilla/docornot)
- [Alt Text Validation](https://huggingface.co/datasets/Mozilla/alt-text-validation)
- A debiased version of COCO 2017: https://cocodataset.org

You can find the code used to create the model here: https://github.com/mozilla/distilvit


# training results

- eval/gen_len 14.99729
- eval/loss 0.17093
- eval/meteor 0.51479
- eval/rouge1 57.8066
- eval/rouge2 35.0888
- eval/rougeL 52.9138
- eval/rougeLsum 52.9101
- eval/runtime 760.2135
- eval/samples_per_second 11.18
- eval/steps_per_second 0.112
- train/epoch 8.0
- train/global_step 11752
- train/learning_rate 0.0
- train/loss 0.1034
- train/total_flos 1.518634875573869e+20
- train/train_loss 0.14875
- train/train_runtime 91405.9053
- train/train_samples_per_second 12.855
- train/train_steps_per_second 0.129