# Training Guide: HRM SRAM/DRAM Learning Performance

Use this guide to train the memory-tiered HRM on **real datasets** and verify its reasoning accuracy.

---

### 1. Dataset Generation
The model needs to learn how to solve puzzles. First, generate a training/test set (e.g., Sudoku).

```bash
# Activate environment
source venv/bin/activate

# Build a small Sudoku dataset (1000 examples)
python dataset/build_sudoku_dataset.py \
    --output-dir data/sudoku-1k \
    --subsample-size 1000 \
    --num-aug 10
```

---

### 2. Start Training
Point the trainer to the tiered architecture configuration.

#### Train the Tiered Model (New)
```bash
python pretrain.py \
    arch=hrm_tiered \
    data_path=data/sudoku-1k \
    epochs=1000 \
    global_batch_size=384
```

#### Train the Baseline Model (Comparison)
```bash
python pretrain.py \
    arch=hrm_v1 \
    data_path=data/sudoku-1k \
    epochs=1000 \
    global_batch_size=384
```

---

### 3. Verify Reasoning Accuracy
Once training is complete (or during training), check the accuracy metrics in your W&B dashboard or via the evaluation script:

```bash
# Replace with the path to your generated checkpoint
python evaluate.py checkpoint=checkpoints/Sudoku_ACT-torch/YOUR_RUN/step_1000
```

**What to look for:**
- **`eval/exact_accuracy`**: Fraction of puzzles solved perfectly.
- **`eval/steps`**: Average number of reasoning steps taken by the ACT (Adaptive Computation Time) module.
- **`eval/q_halt_accuracy`**: How well the model learns when to stop thinking.

---

### 4. Training on ARC (Artificial General Intelligence Benchmark)
To train on the more complex ARC-AGI-2 dataset:

```bash
python dataset/build_arc_dataset.py --output-dir data/arc-2
python pretrain.py arch=hrm_tiered data_path=data/arc-2
```