README.md

metadata

base_model: mistralai/Mistral-7B-v0.1
datasets:
  - generator
library_name: peft
license: apache-2.0
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: mistral-7b-foodrecipe_v2
    results: []

mistral-7b-foodrecipe_v2

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the generator dataset.

Model description

Input a food or dessert (EX: How can we make Miso-Butter Roast Chicken With Acorn Squash Panzanella). Returns a completion of sentences with the recipe of the food.

Intended uses & limitations

For casual use.

Training and evaluation data

Trained and evaluate on Jaspertw177/food_recipe_forLLM_2167947.

Training procedure

Only used 200,000 rows in the training dataset with QLORA.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0001
• train_batch_size: 3
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 6
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 1

Training results

Framework versions

• PEFT 0.11.1
• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1