Semanlink - An empirical analysis of compute-optimal large language model training

An empirical analysis of compute-optimal large language model training

Tags:

About This Document

sl:bookmarkOf : https://www.deepmind.com/blog/an-empirical-analysis-of-compute-optimal-large-language-model-training
sl:creationDate : 2023-01-26
sl:creationTime : 2023-01-26T23:33:11Z

File info

Bookmark of: https://www.deepmind.com/blog/an-empirical-analysis-of-compute-optimal-large-language-model-training

Documents with similar tags (experimental)

Google "We Have No Moat, And Neither Does OpenAI"

Tags:

> low-cost public involvement was enabled
by a vastly cheaper mechanism for fine tuning called low
rank adaptation ()[LoRA](tag:lora)

> **Part of what makes LoRA so effective is that ... it’s stackable.**
>
> By contrast, training giant models from scratch not only
throws away the pretraining, but also any iterative
improvements that have been made on top.

> LoRA updates are very cheap to produce (~$100) for the
most popular model sizes.

> Many of these projects are saving time by training on
small, highly curated datasets...
> These
datasets are built using synthetic methods (e.g. filtering
the best responses from an existing model) and
scavenging from other projects

> Directly Competing With Open Source
Is a Losing Proposition

> Paradoxically, the one clear winner in all of this is Meta.
Because the leaked model was theirs ([LLaMA](tag:llama)), they have
effectively garnered an entire planet's worth of free labor.
Since most open source innovation is happening on top of
their architecture, there is nothing stopping them from
directly incorporating it into their products.

2023-05-04 About

Guillaume Lample sur Twitter : "Today we release LLaMA, 4 foundation models ranging from 7B to 65B parameters..."

Tags:

2023-02-25 About

[2203.14465] STaR: Bootstrapping Reasoning With Reasoning

Tags:

2023-02-07 About

The Flan Collection: Advancing open source methods for instruction tuning – Google AI Blog

Tags:

2023-02-02 About

Characterizing Emergent Phenomena in Large Language Models – Google AI Blog

Tags:

2023-01-26 About

Andrej Karpathy sur Twitter : "Great post (5mo ago) "chinchilla's wild implications" giving context to LLM goldrush shifting from model size to dataset size..."

Tags:

2023-01-05 About

Some remarks on Large Language Models

Tags:

> There turned out to be a phase shift somewhere between 60B parameters and 175B parameters, that made language models super impressive.

> **The performance of current days language models are not obtained by language modeling**
>
>    - [Traditional] LMs are not [grounded](tag:grounded_language_learning)
> 
> **3 conceptual steps between GPT-3 and chatGPT: Instructions, code, RLHF.** The last one is, I think, the least interesting despite getting the most attention
>
> Instruction tuning: For example, the human annotators would write something like "please summarize this text", followed by some text they got, followed by a summary they produced of this text. -> Some symbols ("summarize", "translate", "formal") are used in a consistent way together with the concept/task they denote. And they always appear in the beginning of the text. -> the act of producing a summary grounded to the human concept of "summary"
>
> code: programming language code data, and specifically data that contains both natural language instructions or descriptions (in the form of code comments) and the corresponding programming language code. This produced another very direct form of grounding. the human language describes concepts (or intents), which are then realized in the form of the corresponding programs.
>
> "[RL with Human Feedback](tag:reinforcement_learning_from_human_feedback)". This is a fancy way of saying that the model now observes two humans in a conversation, one playing the role of a user, and another playing the role of "the AI", demonstrating how the AI should respond in different situations. This clearly helps the model learn how dialogs work, and how to keep track of information across dialog states (something that is very hard to learn from just "found" data).

2023-01-03 About

Andrew Trask about large language models: The "bigness" is a temporary flaw, not a permanent feature of progress"

Tags:

2022-03-13 About

[2106.04647] Compacter: Efficient Low-Rank Hypercomplex Adapter Layers

Tags:

2021-09-29 About

How Much Knowledge Can You Pack Into the Parameters of a Language Model?

Tags:

> It has recently been observed that neural language
models trained on unstructured text can
implicitly store and retrieve knowledge using
natural language queries.

indeed, cf. Facebook's paper [Language Models as Knowledge Bases?](/doc/2019/09/_1909_01066_language_models_as)

> In this short paper,
we measure the practical utility of this
approach by fine-tuning pre-trained models to
answer questions without access to any external
context or knowledge.

> we show that a large language
model pre-trained on unstructured text can
attain competitive results on open-domain question
answering benchmarks without any access
to external knowledge

BUT:

>1. state-of-the-art results only with the largest model
which had 11 billion parameters.
>1. “open-book” models
typically provide some indication of what information
they accessed when answering a question
that provides a useful form of interpretability.
In contrast, our model distributes knowledge
in its parameters in an inexplicable way, which
precludes this form of interpretability.
>1. **the maximum-likelihood objective provides no guarantees as to whether
a model will learn a fact or not.**

So, what's the point? To be compared with this [IBM's paper](/doc/2019/09/_1909_04120_span_selection_pre): "a new pre-training task inspired by reading comprehension and an effort to avoid encoding general knowledge in the transformer network itself"

2020-02-11 About