paint-brush

This story draft by @escholar has not been reviewed by an editor, YET.

Additional Details of the Copy and Retrieval Tasks

EScholar: Electronic Academic Papers for Scholars HackerNoon profile picture
EScholar: Electronic Academic Papers for Scholars

EScholar: Electronic Academic Papers for Scholars

@escholar

We publish the best academic work (that's too often lost to peer reviews & the TA's desk) to the global tech community

undefined @escholar
LEARN MORE ABOUT @ESCHOLAR'S
EXPERTISE AND PLACE ON THE INTERNET.

Authors:

(1) Soham De, Google DeepMind and with Equal contributions;

(2) Samuel L. Smith, Google DeepMind and with Equal contributions;

(3) Anushan Fernando, Google DeepMind and with Equal contributions;

(4) Aleksandar Botev, Google DeepMind and with Equal contributions;

(5) George Cristian-Muraru, Google DeepMind and with Equal contributions;

(6) Albert Gu, Work done while at Google DeepMind;

(7) Ruba Haroun, Google DeepMind;

(8) Leonard Berrada, Google DeepMind;

(9) Yutian Chen, Google DeepMind;

(10) Srivatsan Srinivasan, Google DeepMind;

(11) Guillaume Desjardins, Google DeepMind;

(12) Arnaud Doucet, Google DeepMind;

(13) David Budden, Google DeepMind;

(14) Yee Whye Teh, Google DeepMind;

(15) David Budden, Google DeepMind;

(16) Razvan Pascanu, Google DeepMind;

(17) Nando De Freitas, Google DeepMind;

(18) Caglar Gulcehre, Google DeepMind.

Table of Links

1 Introduction

2 Model Architecture

3 Recurrent Models Scale as Efficiently as Transformers

3.1. Scaling curves

3.2. Evaluation on downstream tasks

4 Training Recurrent Models Efficiently on Device and 4.1. Model parallelism for large scale training

4.2. Efficient linear recurrences on device

4.3. Training speed on longer sequences

5. Inference Speed

5.1. A simple model of the decode step

5.2. Results

6. Long Context Modeling and 6.1. Improving next token prediction with longer contexts

6.2. Copy and retrieval capabilities

7. Related Works

8. Conclusion, Acknowledgements, and References


A. RG-LRU Recurrence Gate

B. Complex-Gated Linear Recurrent Unit (CG-LRU)

C. Model Scale Hyper-Parameters

D. Efficient Linear Recurrences on Device

E. The Local Attention Window Size of Griffin

F. Inference Speeds

G. Improving Next Token Prediction with Longer Contexts: Additional Results

H. Additional Details of the Copy and Retrieval Tasks

H. Additional Details of the Copy and Retrieval Tasks

Figure 11 is an illustration of the Selective Copying and Induction Heads tasks.


In the Selective Copying task, the model needs to learn to copy data tokens (coloured tokens in Figure 11) from a sequence while ignoring noise tokens (white tokens in Figure 11). Crossed out tokens in the output in Figure 6 denote tokens that are masked out in the loss.


Figure 11 | An illustration of the Selective Copying (left) and the Induction Heads tasks (right).

Figure 11 | An illustration of the Selective Copying (left) and the Induction Heads tasks (right).


In the Induction Heads task, the model needs to learn to recall the token immediately following a special token (black token in Figure 11). As before, crossed out tokens in the output denote tokens that are masked out in the loss.


This paper is available on arxiv under CC BY 4.0 DEED license.


L O A D I N G
. . . comments & more!

About Author

EScholar: Electronic Academic Papers for Scholars HackerNoon profile picture
EScholar: Electronic Academic Papers for Scholars@escholar
We publish the best academic work (that's too often lost to peer reviews & the TA's desk) to the global tech community

Topics

Around The Web...

Read on Terminal Reader
Read this story in a terminal
 Terminal
Read this story w/o Javascript
Read this story w/o Javascript
 Lite