metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- Gustavosta/Stable-Diffusion-Prompts
model-index:
- name: distilgpt2-magicprompt-SD
results: []
widget:
- text: morning sun over Jakarta
example_title: morning sun
- text: 'WARNING: pip is'
example_title: pip
- text: sentient cheese
example_title: sentient cheese
- text: cheeps are
example_title: cheeps
parameters:
min_length: 16
max_length: 96
no_repeat_ngram_size: 1
do_sample: true
distilgpt2-magicprompt-SD
Generate/augment your prompt, stable diffusion style.
This model is a fine-tuned version of distilgpt2 on the Gustavosta/Stable-Diffusion-Prompts dataset. It achieves the following results on the evaluation set:
- Loss: 1.3089
- eval_steps_per_second = 17.201
- perplexity = 3.7022
example
Results in (DALL-E, but you get the idea):
this distilgpt2 version is probably small/fast enough to be used locally on CPU!
Training and evaluation data
refer to the Gustavosta/Stable-Diffusion-Prompts dataset.
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.001
- train_batch_size: 16
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.7061 | 0.99 | 33 | 2.5859 |
| 2.08 | 1.99 | 66 | 1.9965 |
| 1.7623 | 2.99 | 99 | 1.7248 |
| 1.5408 | 3.99 | 132 | 1.5449 |
| 1.4147 | 4.99 | 165 | 1.4437 |
| 1.3593 | 5.99 | 198 | 1.3768 |
| 1.2703 | 6.99 | 231 | 1.3362 |
| 1.2528 | 7.99 | 264 | 1.3175 |
| 1.1981 | 8.99 | 297 | 1.3091 |
| 1.2117 | 9.99 | 330 | 1.3089 |
Framework versions
- Transformers 4.25.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.6.1
- Tokenizers 0.13.1