|
--- |
|
language: |
|
- es |
|
tags: |
|
- generated_from_trainer |
|
- recipe-generation |
|
|
|
widget: |
|
- text: "<RECIPE_START> <INPUT_START> salmón <NEXT_INPUT> zumo de naranja <NEXT_INPUT> aceite de oliva <NEXT_INPUT> sal <NEXT_INPUT> pimienta <INPUT_END> <INGR_START>" |
|
- text: "<RECIPE_START> <INPUT_START> harina <NEXT_INPUT> azúcar <NEXT_INPUT> huevos <NEXT_INPUT> chocolate <NEXT_INPUT> levadura Royal <INPUT_END> <INGR_START>" |
|
inference: |
|
parameters: |
|
top_k: 50 |
|
top_p: 0.92 |
|
do_sample: True |
|
num_return_sequences: 3 |
|
max_new_tokens: 100 |
|
|
|
--- |
|
|
|
# Model description |
|
|
|
This model is a fine-tuned version of [flax-community/gpt-2-spanish](https://huggingface.co/flax-community/gpt-2-spanish) on a custom dataset (not publicly available). The dataset is made of crawled data from 3 Spanish cooking websites and it contains approximately ~50000 recipes. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5796 |
|
|
|
## Contributors |
|
|
|
- Julián Cendrero ([jucendrero](https://huggingface.co/jucendrero)) |
|
- Silvia Duque ([silBERTa](https://huggingface.co/silBERTa)) |
|
|
|
## How to use it |
|
|
|
```python |
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
|
model_checkpoint = 'gastronomia-para-to2/gastronomia_para_to2' |
|
tokenizer = AutoTokenizer.from_pretrained(model_checkpoint) |
|
model = AutoModelForCausalLM.from_pretrained(model_checkpoint) |
|
``` |
|
|
|
The tokenizer makes use of the following special tokens to indicate the structure of the recipe: |
|
|
|
```python |
|
special_tokens = [ |
|
'<INPUT_START>', |
|
'<NEXT_INPUT>', |
|
'<INPUT_END>', |
|
'<TITLE_START>', |
|
'<TITLE_END>', |
|
'<INGR_START>', |
|
'<NEXT_INGR>', |
|
'<INGR_END>', |
|
'<INSTR_START>', |
|
'<NEXT_INSTR>', |
|
'<INSTR_END>', |
|
'<RECIPE_START>', |
|
'<RECIPE_END>'] |
|
``` |
|
|
|
The input should be of the form: |
|
|
|
```python |
|
<RECIPE_START> <INPUT_START> ingredient_1 <NEXT_INPUT> ingredient_2 <NEXT_INPUT> ... <NEXT_INPUT> ingredient_n <INPUT_END> <INGR_START> |
|
``` |
|
|
|
We are using the following configuration to generate recipes, but feel free to change parameters as needed: |
|
|
|
```python |
|
tokenized_input = tokenizer(input, return_tensors='pt') |
|
output = model.generate(**tokenized_input, |
|
max_length=600, |
|
do_sample=True, |
|
top_p=0.92, |
|
top_k=50, |
|
num_return_sequences=3) |
|
pre_output = tokenizer.decode(output[0], skip_special_tokens=False) |
|
``` |
|
|
|
The recipe ends where the \<RECIPE_END\> special token appears for the first time. |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 2e-05 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 6 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 0.6213 | 1.0 | 5897 | 0.6214 | |
|
| 0.5905 | 2.0 | 11794 | 0.5995 | |
|
| 0.5777 | 3.0 | 17691 | 0.5893 | |
|
| 0.574 | 4.0 | 23588 | 0.5837 | |
|
| 0.5553 | 5.0 | 29485 | 0.5807 | |
|
| 0.5647 | 6.0 | 35382 | 0.5796 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.17.0 |
|
- Pytorch 1.11.0+cu102 |
|
- Datasets 2.0.0 |
|
- Tokenizers 0.11.6 |
|
|
|
## References |
|
The list of special tokens used for generation recipe structure has been taken from: |
|
[RecipeNLG: A Cooking Recipes Dataset for Semi-Structured Text Generation](https://www.aclweb.org/anthology/2020.inlg-1.4.pdf). |
|
|
|
|
