---
license: apache-2.0
base_model: distilgpt2
tags:
- generated_from_trainer
model-index:
- name: distilgpt2-sd
  results: []
datasets:
- Gustavosta/Stable-Diffusion-Prompts
---

<!-- 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. -->

# distilgpt2-sd

This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on [Stable-Diffusion-Prompt](https://huggingface.co/datasets/Gustavosta/Stable-Diffusion-Prompts) dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4481

## 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: 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: 3

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 3.36          | 0.05  | 500   | 2.8209          |
| 2.8086        | 0.11  | 1000  | 2.5757          |
| 2.6126        | 0.16  | 1500  | 2.4096          |
| 2.4771        | 0.22  | 2000  | 2.3027          |
| 2.3986        | 0.27  | 2500  | 2.2076          |
| 2.3148        | 0.33  | 3000  | 2.1547          |
| 2.237         | 0.38  | 3500  | 2.0825          |
| 2.1731        | 0.43  | 4000  | 2.0334          |
| 2.1256        | 0.49  | 4500  | 1.9806          |
| 2.081         | 0.54  | 5000  | 1.9345          |
| 2.0677        | 0.6   | 5500  | 1.9053          |
| 1.9794        | 0.65  | 6000  | 1.8691          |
| 2.0072        | 0.71  | 6500  | 1.8429          |
| 1.9597        | 0.76  | 7000  | 1.8061          |
| 1.9318        | 0.82  | 7500  | 1.7857          |
| 1.9283        | 0.87  | 8000  | 1.7610          |
| 1.8959        | 0.92  | 8500  | 1.7378          |
| 1.8626        | 0.98  | 9000  | 1.7185          |
| 1.8126        | 1.03  | 9500  | 1.7040          |
| 1.7789        | 1.09  | 10000 | 1.6855          |
| 1.7794        | 1.14  | 10500 | 1.6756          |
| 1.7284        | 1.2   | 11000 | 1.6529          |
| 1.7478        | 1.25  | 11500 | 1.6384          |
| 1.7065        | 1.3   | 12000 | 1.6321          |
| 1.7092        | 1.36  | 12500 | 1.6133          |
| 1.6897        | 1.41  | 13000 | 1.6146          |
| 1.6902        | 1.47  | 13500 | 1.5952          |
| 1.6888        | 1.52  | 14000 | 1.5792          |
| 1.6862        | 1.58  | 14500 | 1.5730          |
| 1.6458        | 1.63  | 15000 | 1.5661          |
| 1.6594        | 1.68  | 15500 | 1.5537          |
| 1.6486        | 1.74  | 16000 | 1.5484          |
| 1.6556        | 1.79  | 16500 | 1.5360          |
| 1.6187        | 1.85  | 17000 | 1.5264          |
| 1.6377        | 1.9   | 17500 | 1.5223          |
| 1.6129        | 1.96  | 18000 | 1.5180          |
| 1.6025        | 2.01  | 18500 | 1.5030          |
| 1.5697        | 2.06  | 19000 | 1.4991          |
| 1.5616        | 2.12  | 19500 | 1.5012          |
| 1.558         | 2.17  | 20000 | 1.4984          |
| 1.549         | 2.23  | 20500 | 1.4809          |
| 1.5048        | 2.28  | 21000 | 1.4827          |
| 1.5207        | 2.34  | 21500 | 1.4740          |
| 1.5097        | 2.39  | 22000 | 1.4699          |
| 1.541         | 2.45  | 22500 | 1.4701          |
| 1.5355        | 2.5   | 23000 | 1.4637          |
| 1.5318        | 2.55  | 23500 | 1.4609          |
| 1.5352        | 2.61  | 24000 | 1.4580          |
| 1.5202        | 2.66  | 24500 | 1.4566          |
| 1.5073        | 2.72  | 25000 | 1.4547          |
| 1.5462        | 2.77  | 25500 | 1.4520          |
| 1.5347        | 2.83  | 26000 | 1.4491          |
| 1.52          | 2.88  | 26500 | 1.4488          |
| 1.5154        | 2.93  | 27000 | 1.4475          |
| 1.4855        | 2.99  | 27500 | 1.4481          |


### Framework versions

- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3