ingredients_to_recipe_llama-3.2-model

This model is a fine-tuned version of meta-llama/Llama-3.2-1B on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6841

Model description

This is llama 3.2 1B fine-tuned on an ingredients_to_recipe dataset.

Intended uses & limitations

For best performance, prompt should follow this format: [INST] Generate a cooking recipe using the following ingredients:1 c. firmly packed brown sugar, 1/2 c. evaporated milk, 1/2 tsp. vanilla, 1/2 c. broken nuts (pecans), 2 Tbsp. butter or margarine, 3 1/2 c. bite size shredded rice biscuits [/INST]

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: 24
• eval_batch_size: 24
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.7335	1.0	2500	0.6922
0.6345	2.0	5000	0.6790
0.6034	3.0	7500	0.6841

Framework versions

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