---
library_name: transformers
tags:
- generated_from_trainer
- image-to-text
- image-captioning
model-index:
- name: ViT-GPT2
  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-GPT2

This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.4134
- Rouge2 Fmeasure: 0.1166

## 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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Rouge2 Fmeasure |
|:-------------:|:------:|:----:|:---------------:|:---------------:|
| No log        | 0.9987 | 496  | 2.4901          | 0.1077          |
| 2.5089        | 1.9995 | 993  | 2.4292          | 0.1141          |
| 2.4103        | 2.9962 | 1488 | 2.4134          | 0.1166          |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.0
- Datasets 3.0.0
- Tokenizers 0.19.1