metadata
library_name: transformers
license: apache-2.0
base_model: distilgpt2
tags:
- generated_from_trainer
datasets:
- recipe_nlg
model-index:
- name: distilgpt2-finetuned-recipe-nlg-generator
results: []
distilgpt2-finetuned-recipe-nlg-generator
This model is a fine-tuned version of distilgpt2 on the recipe_nlg dataset. It achieves the following results on the evaluation set:
- Loss: 6.0133
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.0675 | 1.0 | 256 | 5.7808 |
| 6.0315 | 2.0 | 512 | 5.7849 |
| 5.8136 | 3.0 | 768 | 5.8173 |
| 5.6857 | 4.0 | 1024 | 5.8658 |
| 5.6426 | 5.0 | 1280 | 5.9132 |
| 5.5854 | 6.0 | 1536 | 5.9587 |
| 5.5609 | 7.0 | 1792 | 5.9801 |
| 5.5196 | 8.0 | 2048 | 5.9917 |
| 5.4844 | 9.0 | 2304 | 6.0054 |
| 5.5273 | 10.0 | 2560 | 6.0133 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.2.0
- Tokenizers 0.19.1