---
license: mit
base_model: microsoft/git-base
tags:
- generated_from_trainer
model-index:
- name: pokemon_captions
  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. -->

# pokemon_captions

This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 6.8347
- Wer Score: 36.5683

## 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|:-------------:|:-----:|:----:|:---------------:|:---------:|
| 9.5449        | 0.21  | 10   | 8.4043          | 75.6190   |
| 8.092         | 0.43  | 20   | 7.6198          | 76.5618   |
| 7.4582        | 0.64  | 30   | 7.1177          | 60.0286   |
| 7.0634        | 0.85  | 40   | 6.8347          | 36.5683   |


### Framework versions

- Transformers 4.35.0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1