---
library_name: transformers
license: mit
base_model: microsoft/git-base
tags:
- generated_from_trainer
model-index:
- name: git-base-caption
  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-caption

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: 6.6179
- Wer Score: 9.0625

## 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|:-------------:|:-----:|:----:|:---------------:|:---------:|
| 10.1592       | 10.0  | 10   | 8.7538          | 31.2656   |
| 8.2408        | 20.0  | 20   | 7.7825          | 31.5      |
| 7.4378        | 30.0  | 30   | 7.1866          | 15.625    |
| 6.9092        | 40.0  | 40   | 6.7962          | 9.375     |
| 6.5994        | 50.0  | 50   | 6.6179          | 9.0625    |


### Framework versions

- Transformers 4.48.2
- Pytorch 2.5.1+cu124
- Tokenizers 0.21.0