results

This model is a fine-tuned version of google/flan-t5-small on an Shengtao/recipe. It achieves the following results on the evaluation set:

• Loss: 0.1664

Model description

It generates a recipe name using the user's list of ingredients as input.

Intended uses & limitations

More information needed

Training and evaluation data

Data used from Shengtao/recipe dataset. Used title as evaluation data Used ingredients as training data

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: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.1994	1.0	4091	0.1716
0.1917	2.0	8182	0.1664

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1