---
library_name: transformers
license: mit
base_model: microsoft/git-base
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: git-base-one-entrance-dungeons
  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. -->

# git-base-one-entrance-dungeons

This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co./microsoft/git-base) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 6.4972
- Wer Score: 39.8

## 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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|:-------------:|:-----:|:----:|:---------------:|:---------:|
| 8.3012        | 2.5   | 10   | 8.0024          | 140.2     |
| 7.8744        | 5.0   | 20   | 7.5821          | 140.4     |
| 7.4706        | 7.5   | 30   | 7.2110          | 140.4     |
| 7.1213        | 10.0  | 40   | 6.9042          | 100.4     |
| 6.85          | 12.5  | 50   | 6.6843          | 47.8      |
| 6.6704        | 15.0  | 60   | 6.5571          | 40.6      |
| 6.5787        | 17.5  | 70   | 6.5053          | 40.0      |
| 6.5497        | 20.0  | 80   | 6.4972          | 39.8      |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1