---
license: mit
base_model: deepset/gelectra-large-germanquad
tags:
- generated_from_trainer
model-index:
- name: Finetuned_Question_Answering_Model
  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. -->

# Finetuned_Question_Answering_Model

This model is a fine-tuned version of [deepset/gelectra-large-germanquad](https://huggingface.co/deepset/gelectra-large-germanquad) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0130

## 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: 5
- eval_batch_size: 5
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.792         | 1.0   | 3    | 0.0385          |
| 0.4079        | 2.0   | 6    | 0.0418          |
| 0.1837        | 3.0   | 9    | 0.0511          |
| 0.0175        | 4.0   | 12   | 0.0573          |
| 0.0426        | 5.0   | 15   | 0.0547          |
| 0.0108        | 6.0   | 18   | 0.0438          |
| 0.0117        | 7.0   | 21   | 0.0276          |
| 0.0255        | 8.0   | 24   | 0.0184          |
| 0.0087        | 9.0   | 27   | 0.0143          |
| 0.0041        | 10.0  | 30   | 0.0130          |


### Framework versions

- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2