---
library_name: transformers
license: apache-2.0
base_model: distilgpt2
tags:
- generated_from_trainer
model-index:
- name: debiased_gpt_2
  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. -->

# debiased_gpt_2

This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6430

## 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: 8
- eval_batch_size: 8
- seed: 42
- 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 |
|:-------------:|:-----:|:----:|:---------------:|
| No log        | 1.0   | 4    | 1.9343          |
| No log        | 2.0   | 8    | 1.8912          |
| No log        | 3.0   | 12   | 1.6980          |
| No log        | 4.0   | 16   | 1.5873          |
| No log        | 5.0   | 20   | 1.5396          |
| No log        | 6.0   | 24   | 1.4100          |
| No log        | 7.0   | 28   | 1.3086          |
| No log        | 8.0   | 32   | 1.2451          |
| No log        | 9.0   | 36   | 1.1922          |
| No log        | 10.0  | 40   | 1.0959          |
| No log        | 11.0  | 44   | 1.0326          |
| No log        | 12.0  | 48   | 0.9796          |
| No log        | 13.0  | 52   | 0.9345          |
| No log        | 14.0  | 56   | 0.9033          |
| No log        | 15.0  | 60   | 0.8493          |
| No log        | 16.0  | 64   | 0.8235          |
| No log        | 17.0  | 68   | 0.8197          |
| No log        | 18.0  | 72   | 0.7852          |
| No log        | 19.0  | 76   | 0.7588          |
| No log        | 20.0  | 80   | 0.7384          |
| No log        | 21.0  | 84   | 0.7320          |
| No log        | 22.0  | 88   | 0.7220          |
| No log        | 23.0  | 92   | 0.7097          |
| No log        | 24.0  | 96   | 0.7019          |
| No log        | 25.0  | 100  | 0.6938          |
| No log        | 26.0  | 104  | 0.6912          |
| No log        | 27.0  | 108  | 0.6869          |
| No log        | 28.0  | 112  | 0.6760          |
| No log        | 29.0  | 116  | 0.6719          |
| No log        | 30.0  | 120  | 0.6732          |
| No log        | 31.0  | 124  | 0.6657          |
| No log        | 32.0  | 128  | 0.6610          |
| No log        | 33.0  | 132  | 0.6611          |
| No log        | 34.0  | 136  | 0.6624          |
| No log        | 35.0  | 140  | 0.6622          |
| No log        | 36.0  | 144  | 0.6595          |
| No log        | 37.0  | 148  | 0.6564          |
| No log        | 38.0  | 152  | 0.6523          |
| No log        | 39.0  | 156  | 0.6498          |
| No log        | 40.0  | 160  | 0.6493          |
| No log        | 41.0  | 164  | 0.6502          |
| No log        | 42.0  | 168  | 0.6503          |
| No log        | 43.0  | 172  | 0.6485          |
| No log        | 44.0  | 176  | 0.6471          |
| No log        | 45.0  | 180  | 0.6466          |
| No log        | 46.0  | 184  | 0.6458          |
| No log        | 47.0  | 188  | 0.6449          |
| No log        | 48.0  | 192  | 0.6438          |
| No log        | 49.0  | 196  | 0.6432          |
| No log        | 50.0  | 200  | 0.6430          |


### Framework versions

- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.20.3