---
base_model: mistralai/Mistral-7B-v0.1
datasets: trl-lib/math_shepherd
library_name: transformers
model_name: Mistral-7B-v0.1-Math-Shepherd-PRM-0.1
tags:
- generated_from_trainer
- trl
- stepwise-reward-trainer
licence: license
---

# Model Card for Mistral-7B-v0.1-Math-Shepherd-PRM-0.1

This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the [trl-lib/math_shepherd](https://huggingface.co/datasets/trl-lib/math_shepherd) dataset.
It has been trained using [TRL](https://github.com/huggingface/trl).

## Quick start

Example 1

```python
from datasets import load_dataset
from transformers import pipeline

pipe = pipeline("token-classification", model="plaguss/Mistral-7B-v0.1-Math-Shepherd-PRM-0.1")
dataset = load_dataset("trl-lib/math_shepherd")
example = dataset["test"][10]

print("\n".join((example["prompt"], *example["completions"])))
for idx in range(1, len(example["completions"])+1):
    text = "\n".join((example["prompt"], *example["completions"][0:idx])) + "\n"
    score = float(pipe(text)[-1]["score"])
    print(f"Step {idx}\tScore: {score:.4f}\tLabel: {example['labels'][idx-1]}")

# Asking to truncate to max_length but no maximum length is provided and the model has no predefined maximum length. Default to no truncation.
# Step 1  Score: 1.00     Label: True
# Step 2  Score: 1.00     Label: True
# Step 3  Score: 1.00     Label: True
# Step 4  Score: 0.96     Label: True
# Step 5  Score: 0.95     Label: True
# Step 6  Score: 0.88     Label: False
# Step 7  Score: 0.73     Label: False
# Step 8  Score: 0.86     Label: False
# Step 9  Score: 0.96     Label: False
```

Original case from the Math-Shepherd paper

```python
from datasets import load_dataset
from transformers import pipeline

pipe = pipeline("token-classification", model="plaguss/Mistral-7B-v0.1-Math-Shepherd-PRM-0.1", device="cuda")

examples = [
    {
        "prompt": "Janet\u2019s ducks lay 16 eggs per day. She eats three for breakfast every morning and bakes muffins for her friends every day with four. She sells the remainder at the farmers' market daily for $2 per fresh duck egg. How much in dollars does she make every day at the farmers' market?",
        "completions": [
            "Step 1: Janet's ducks lay 16 eggs per day.",
            'Step 2: She eats three for breakfast every morning, so she has 16 - 3 = 13 eggs left.',
            'Step 3: She bakes muffins for her friends every day with four eggs, so she has 13 - 4 = 9 eggs left.',
            "Step 4: She sells the remainder at the farmers' market daily for $2 per fresh duck egg, so she makes 9 * $2 = $18 every day at the farmers' market. The answer is: 18"
        ],
        "labels": [True, True, True, True]
    },
    {
        "prompt": "Janet\u2019s ducks lay 16 eggs per day. She eats three for breakfast every morning and bakes muffins for her friends every day with four. She sells the remainder at the farmers' market daily for $2 per fresh duck egg. How much in dollars does she make every day at the farmers' market?",
        "completions": [
            "Step 1: Janet's ducks lay 16 eggs per day.",
            'Step 2: She eats three for breakfast every morning, so she has 16 - 3 = 13 eggs left.',
            'Step 3: She bakes muffins for her friends every day with four eggs, so she has 13 - 4 = 9 eggs left.',
            "Step 4: She sells the remainder at the farmers' market daily for $2 per fresh duck egg, so she makes 9 * $2 = $18 every day at the farmers' market. The answer is: 17"
        ],
        "labels": [True, True, True, False]
    },
    
]

for i, example in enumerate(examples):
    print(f"- Example {i}:")
    for idx in range(1, len(example["completions"])+1):
        text = "\n".join((example["prompt"], *example["completions"][0:idx])) + "\n"
        score = float(pipe(text)[-1]["score"])
        print(f"Step {idx}\tScore: {score:.2f}\tLabel: {example['labels'][idx-1]}")

# - Example 0:
# Step 1  Score: 1.00     Label: True
# Step 2  Score: 1.00     Label: True
# Step 3  Score: 1.00     Label: True
# Step 4  Score: 1.00     Label: True
# - Example 1:
# Step 1  Score: 1.00     Label: True
# Step 2  Score: 1.00     Label: True
# Step 3  Score: 1.00     Label: True
# Step 4  Score: 0.98     Label: False
```

## Training procedure

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/plaguss/huggingface/runs/lnkexnro)

This model was trained with Stepwise Reward.

### Framework versions

- TRL: 0.13.0.dev0
- Transformers: 4.46.0.dev0
- Pytorch: 2.4.1
- Datasets: 3.0.1
- Tokenizers: 0.20.1

## Citations

Cite Stepwise Reward as:

```bibtex
@article{uesato2022solving,
    title        = {Solving Math Word Problems With Process- and Outcome-Based Feedback},
    author       = {Uesato, Jonathan and Kushman, Nate and Kumar, Ramana and Song, Francis and Siegel, Noah and Wang, Lisa and Creswell, Antonia and Irving, Geoffrey and Higgins, Irina},
    year         = 2022,
    journal      = {arXiv preprint arXiv:2211.14275}
}
```

Cite TRL as:
    
```bibtex
@misc{vonwerra2022trl,
	title        = {{TRL: Transformer Reinforcement Learning}},
	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
	year         = 2020,
	journal      = {GitHub repository},
	publisher    = {GitHub},
	howpublished = {\url{https://github.com/huggingface/trl}}
}
```