metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- recipe_nlg_lite
model-index:
- name: recipe-generation
results: []
recipe-generation
This model is a fine-tuned version of distilgpt2 on the recipe_nlg_lite dataset. It achieves the following results on the evaluation set:
- Loss: 1.1328
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4765 | 1.0 | 765 | 1.2390 |
| 1.222 | 2.0 | 1530 | 1.1797 |
| 1.1884 | 3.0 | 2295 | 1.1524 |
| 1.1446 | 4.0 | 3060 | 1.1371 |
| 1.1458 | 5.0 | 3825 | 1.1328 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2