Charley890/adaption_adaptive_math_2

Overview

Adaptive Math 2

A mathematics-specialized instruction dataset designed to improve reasoning, structured problem solving, and educational AI assistants through supervised fine-tuning with Adaptation Labs AutoScientist.

Research Snapshot

Property	Value
Domain	Mathematics
Dataset Type	Instruction Tuning
Framework	Adaptation Labs AutoScientist
Base Model	Llama-4 Scout 17B
Fine-tuning	LoRA (SFT)
Grade	A
Quality Score	9.5 / 10

Dataset Highlights

Adaptive Math 2 focuses on educational mathematical reasoning rather than simple answer prediction.

Covers

• Algebra
• Geometry
• Arithmetic
• Number Theory
• Statistics
• Word Problems
• Mathematical Reasoning
• Multi-step Solutions

Characteristics

✅ Structured instruction format

✅ Educational explanations

✅ Curriculum-oriented questions

✅ Reasoning-aware responses

✅ Clean supervised fine-tuning format

Example Dataset Samples

Example 1

Instruction

Solve:
4x - 9 = 19

Expected Response

4x = 28

x = 7

---

Example 2

Instruction

A triangle has angles of 45° and 65°.

Find the third angle.

Expected Response

180° − (45° + 65°)

= 70°

Educational Impact

Adaptive Math 2 is intended for:

• AI tutors
• Educational assistants
• Mathematical reasoning
• Homework support
• Classroom demonstrations
• STEM education
• Benchmark evaluation

The dataset emphasizes transparent reasoning instead of answer memorization.

Acknowledgement

Adaptive Math 2 was developed using the Adaption Lab AutoScientist pipeline with Meta Llama 4 Scout 17B as the foundation model.

Special thanks to:

• Adaption Lab for the AutoScientist training and evaluation platform.
• Meta AI for the Llama 4 Scout base model.
• Hugging Face for open model hosting and distribution.
• Kaggle for dataset publication and community accessibility.

This project demonstrates how adaptive instruction datasets can improve mathematical reasoning, instruction following, and educational AI through efficient LoRA fine-tuning.

📊 Model Performance

{
  "job_id": "8db3bddd-326c-44ba-8440-2456d10d33f2",
  "training_experiment_id": "78a0fd31-7d13-40cf-bc55-fb2d2bf9e92c",
  "original_model_name": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
  "trained_model_name": "adaption_adaptive_math_2",
  "training_method": "sft",
  "training_type": "lora",
  "data_format": "chat",
  "hyperparams": {
    "lora": "true",
    "lora_r": 16,
    "n_evals": 5,
    "n_epochs": 5,
    "batch_size": "max",
    "lora_alpha": 32,
    "lora_dropout": 0,
    "min_lr_ratio": 0.1,
    "warmup_ratio": 0.03,
    "weight_decay": 0,
    "learning_rate": 0.00005,
    "max_grad_norm": 2,
    "base_model_size": "109B",
    "train_on_inputs": "false",
    "training_method": "sft",
    "lr_scheduler_type": "linear",
    "scheduler_num_cycles": 0.5,
    "lora_trainable_modules": "k_proj,o_proj,q_proj,v_proj,shared_expert.gate_proj,shared_expert.up_proj,shared_expert.down_proj,feed_forward.gate_proj,feed_forward.up_proj,feed_forward.down_proj"
  }
}

Training Data

The model was trained on 1,306 rows of adapted data with the following domain distribution: math (77%), code (8%), science (8%), academic-education (8%).

Model Evaluation

The model was evaluated on an in-distribution held-out test set as well as a broader domain-specific test set to measure generalization.

Domain	Win rate vs. base model
math	66%

How to use

pip install torch transformers peft

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

BASE = "meta-llama/Llama-4-Scout-17B-16E-Instruct"
ADAPTER = "<this-repo-id>"

device = "cuda" if torch.cuda.is_available() else "cpu"
dtype = torch.float32 if device == "cpu" else torch.bfloat16

base = AutoModelForCausalLM.from_pretrained(BASE, dtype=dtype).to(device)
model = PeftModel.from_pretrained(base, ADAPTER)
# Optional: merge the LoRA weights into the base for faster inference
model = model.merge_and_unload()
model.eval()

tokenizer = AutoTokenizer.from_pretrained(BASE)
messages = [{"role": "user", "content": "Hello!"}]
text = tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(device)

with torch.inference_mode():
    out = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))