README.md

---
license: mit
base_model: Qwen/Qwen2.5-1.5B-Instruct
tags:
- algorithmic-sft
- lora
- formal-logic
- algorithmic-template
library_name: peft
---

# Formal Logic — Truth Table

LoRA adapter for **Qwen/Qwen2.5-1.5B-Instruct** fine-tuned on formal logic via **Algorithmic Template SFT**.

Part of the [Algorithmic SFT vs Distillation](https://huggingface.co/collections/reasoning-degeneration-dev/algorithmic-sft-vs-distillation) experiment studying whether deterministic algorithmic templates teach procedural reasoning more effectively than distillation from large reasoning models.

## Training

| Parameter | Value |
|-----------|-------|
| **Base model** | Qwen/Qwen2.5-1.5B-Instruct |
| **Method** | Algorithmic Template SFT |
| **Framework** | LLaMA-Factory (SFT stage) |
| **LoRA rank** | 64 |
| **LoRA target** | all linear layers |
| **Learning rate** | 1e-4 |
| **Epochs** | 3 |
| **Batch size** | 4 (grad accum 4) |
| **Cutoff length** | 32,768 tokens |
| **Training data** | 5,000 deterministic truth-table enumeration traces (d5) |

## Evaluation (v3, MAX_TOKENS=32768)

| Split | Accuracy |
|-------|----------|
| Test (in-distribution) | 100.0% |
| Harder variant | 93.0% |
| Structural OOD | 90.2% |

## Notes

Also near-perfect. Slightly behind bottom-up on generalization.

## Usage

```python
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")
model = PeftModel.from_pretrained(base, "reasoning-degeneration-dev/algo-sft-formal-logic-truth-table")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")
```

## Related Datasets

- [Training data](https://huggingface.co/datasets/reasoning-degeneration-dev/algorithmic-sft-training-data-v1) (63K algo traces)
- [Distillation data](https://huggingface.co/datasets/reasoning-degeneration-dev/algorithmic-sft-distillation-training-data-v1) (24K QwQ traces)
- [Eval results](https://huggingface.co/datasets/reasoning-degeneration-dev/algorithmic-sft-full-eval-v3) (aggregate scores)
- [Eval questions](https://huggingface.co/datasets/reasoning-degeneration-dev/algorithmic-sft-eval-sets-v1) (11K test/val/harder/OOD)