---
library_name: peft
tags:
- generated_from_trainer
base_model: ml6team/gpt2-small-german-finetune-oscar
model-index:
- name: ml6team-gpt2-small-german-finetune-oscar-peft
  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. -->

# ml6team-gpt2-small-german-finetune-oscar-peft

This model is a fine-tuned version of [ml6team/gpt2-small-german-finetune-oscar](https://huggingface.co/ml6team/gpt2-small-german-finetune-oscar) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 4.5772

## 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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 5.173         | 1.0   | 210  | 4.7734          |
| 4.6792        | 2.0   | 420  | 4.6458          |
| 4.5685        | 3.0   | 630  | 4.6042          |
| 4.2199        | 4.0   | 840  | 4.5872          |
| 4.7324        | 5.0   | 1050 | 4.5797          |
| 5.4576        | 6.0   | 1260 | 4.5772          |


### Framework versions

- PEFT 0.8.2
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2