---
license: apache-2.0
base_model: answerdotai/ModernBERT-base
datasets:
- biglam/on_the_books
language:
- en
pipeline_tag: text-classification
tags:
- legal
- classification
- jim-crow
- modernbert
metrics:
- f1
- accuracy
- precision
- recall
model-index:
- name: jim-crow-laws-ml-agent
  results:
  - task:
      type: text-classification
      name: Text Classification
    dataset:
      name: biglam/on_the_books
      type: biglam/on_the_books
      split: test
    metrics:
    - name: F1
      type: f1
      value: 0.9487
    - name: Accuracy
      type: accuracy
      value: 0.9701
    - name: Precision
      type: precision
      value: 0.9367
    - name: Recall
      type: recall
      value: 0.961
---

# Jim Crow Law Classifier (ModernBERT-base)

A text classification model fine-tuned on [biglam/on_the_books](https://huggingface.co/datasets/biglam/on_the_books) to identify Jim Crow laws in historical US legislative text.

## Model Description

This model classifies sections of US state legislation as either **Jim Crow laws** (discriminatory laws targeting racial minorities) or **non-Jim Crow laws**. It was fine-tuned from [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base), which supports up to 8,192 tokens of context.

## Performance

Evaluated on a stratified 15% held-out test set (268 samples):

| Metric | Score |
|--------|-------|
| **F1** | **0.9487** |
| Accuracy | 0.9701 |
| Precision | 0.9367 |
| Recall | 0.9610 |

## Training Details

- **Base model**: answerdotai/ModernBERT-base (149M parameters)
- **Dataset**: biglam/on_the_books (1,785 samples total; 1,517 train / 268 test)
- **Max sequence length**: 1024 tokens
- **Epochs**: 5 (best checkpoint at epoch 5 by F1)
- **Batch size**: 16
- **Learning rate**: 2e-5 with linear decay
- **Warmup**: 6% of training steps
- **Weight decay**: 0.01
- **Hardware**: NVIDIA T4 GPU
- **Training time**: ~8 minutes

## Usage

```python
from transformers import pipeline

classifier = pipeline("text-classification", model="davanstrien/jim-crow-laws-ml-agent")

text = "The Commission shall provide separate sleeping quarters and separate eating space for the different races."
result = classifier(text)
print(result)
# [{'label': 'jim_crow', 'score': 0.99...}]
```

## Dataset

The [On the Books](https://huggingface.co/datasets/biglam/on_the_books) dataset contains 1,785 sections of North Carolina state legislation from the Jim Crow era, annotated by historians as either Jim Crow laws or non-Jim Crow laws. The dataset is imbalanced: 71% non-Jim Crow, 29% Jim Crow.

## Labels

- `no_jim_crow` (0): Non-discriminatory legislation
- `jim_crow` (1): Jim Crow law (racially discriminatory legislation)

## Limitations

- Trained only on North Carolina legislation; may not generalize to other states
- Historical language patterns may not transfer to modern legal text
- The model may be biased toward the specific annotation criteria used in the dataset