|
--- |
|
tags: |
|
- addition |
|
- mathematics |
|
license: apache-2.0 |
|
library_name: transformers |
|
accuracy_add: 0.999999 |
|
train_loss: 3e-09. |
|
--- |
|
# QuantaMaths: `add_d8_l2_h3_t45K_s173289` |
|
|
|
This repository contains a transformer model that can predict addition questions. |
|
|
|
### Model-specific metadata |
|
- **Operation type**: addition |
|
- **Num digits**: 8 |
|
- **Layers**: 2 |
|
- **Attention Heads**: 3 |
|
- **Training steps**: 45,000 |
|
- **Random seed**: 173289 |
|
|
|
**Contents**: |
|
- `model.pth`: The trained transformer model. |
|
- `training_loss.json`: Data gathered during model training (used to plot "loss over training batches"). |
|
- `behaviors.json`: Facts gathered about the model by direct inspection (attention pattern data, PCA data, digit impact data, etc.). |
|
- `features.json`: Facts gathered about hypothesized algorithm features via experimentation, e.g. node P12L0H1 implements the feature A3.ST. |
|
|
|
**Provenance**: |
|
- `model.pth` and `training_loss.json` were created by [QuantaMathsTrain.ipynb](https://github.com/PhilipQuirke/quanta_maths/blob/main/notebooks/QuantaMathsTrain.ipynb). |
|
- `behaviors.json` and `features.json` were created by [QuantaMathsAnalyse.ipynb](https://github.com/PhilipQuirke/quanta_maths/blob/main/notebooks/QuantaMathsAnalyse.ipynb). |
|
- The JSON files are used by [QuantaMathsAlgorithm.ipynb](https://github.com/PhilipQuirke/quanta_maths/blob/main/notebooks/QuantaMathsAlgorithm.ipynb). |
|
|
|
**Folder name details**: |
|
- "add", "sub", or "mix": The types of questions the model can predict. |
|
- "d5" to "d20": How many digits the model handles (e.g. a d5 sub model can predict the answer in 123450-345670=-0123230). |
|
- "l1", "l2", or "l3": The number of layers in the model. |
|
- "h3" or "h4": The number of attention heads in the model. |
|
- "t15K" to "t85K", etc.: The number of batches the model was trained on. |
|
- "s372001", etc.: The random seed used in model training. |
|
|
|
|
|
|
