PhilipQuirke/QuantaMaths_mix_d8_l3_h4_t60K_s173289

QuantaMaths: mix_d8_l3_h4_t60K_s173289

This repository contains a transformer model that can predict both addition and subtraction questions.

Model-specific metadata

• Operation type: mixed
• Num digits: 8
• Layers: 3
• Attention Heads: 4
• Training steps: 60,000
• 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.
• behaviors.json and features.json were created by QuantaMathsAnalyse.ipynb.
• The JSON files are used by 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.