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

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: 0.0740
- Wer Score: 1.1823

## 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
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use 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

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Wer Score |
|:-------------:|:-------:|:----:|:---------------:|:---------:|
| 6.6765        | 7.1538  | 50   | 4.5396          | 23.2812   |
| 2.4289        | 14.3077 | 100  | 0.8224          | 11.4010   |
| 0.2957        | 21.4615 | 150  | 0.1013          | 0.6562    |
| 0.0408        | 28.6154 | 200  | 0.0741          | 1.8333    |
| 0.019         | 35.7692 | 250  | 0.0733          | 3.5938    |
| 0.0134        | 42.9231 | 300  | 0.0740          | 1.1823    |


### Framework versions

- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0