Hacker News Reader

Comment by doctoboggan | Hacker News Reader

I am a little concerned that they have only about 60% of the code tokens (GitHub and stackexchange). Given that so far the only concrete use case I have for LLMs is coding assistance I wouldn't want this open source model to be and less quality in that area.

In your opinion do you think this will hamper the model at all? Or is it still more than enough to get good coding assistance?

View on HN

Nice catch! We sampled the github dataset to match the total # tokens seen by LLaMA during training: ~64B tokens (they only pass through 0.64 of their total Github dataset according to the paper). We have a lot of Github data and will make them available soon. Note, we also have not built this for compute optimal training. We are following LLaMA's lead and are training on more data for longer to optimize for quality, not compute.

Very good to hear that you are optimizing for inference rather than training. I’ve tried llama and its various instruction tuned siblings and have yet to get equivalent performance to gpt-3.5 on coding tasks. Seeing how the base model performed relative to gpt-3 on the various benchmarks gives me hope that the difference is just in RLHF or other fine tuning steps. I really hope the community is able to get there, Especially if the resulting model is able to be quantized with minimal loss.

I wonder if it would make sense to create tokens for each emoji so they don't have to be multi-token. Especially considering people have experimented with using them for makeshift compression.

Thank you for developing the pipeline and amassing considerable compute for gathering and preprocessing this dataset!

I'm not sure if this is the right place to ask about this, but could you consider training an LLM using a more advanced, sparse transformer architecture (specifically, "Terraformer" from this paper https://arxiv.org/abs/2111.12763 and this codebase https://github.com/google/trax/blob/master/trax/models/resea... by Google Brain and OpenAI)? I understand the pressure to focus on training a straightforward LLaMA replication, but of course you see that it's a legacy dense architecture which limits its inference performance. This new architecture is not just an academic curiosity but is already validated at scale by Google, providing 10x+ inference performance boost on the same hardware.

Frankly, the community's compute budget - for training and for inference - isn't infinite, and neither is the public's interest in models that do not have advantage (at least in convenience) over closed-source ones; and so we should utilize both those resources as efficiently as possible. It could be a big step forward if you trained at least LLaMA-Terraformer-7B and 13B foundation models on the whole dataset.

As mentioned in the post, the smaller models are trained well past "compute-optimal" amounts of data and I would expect are well into diminishing returns. On the other hand, large models are good one-shot and few-shot learners, and might be able to pick up enough context from your prompt alone to be useable, even if it wasn't specifically trained on your use case.

In this context compute optimal isn't quite the same as diminishing returns. If you look at the loss graphs in the Llama paper, you can see that even the curves for the smaller models were still going down at the time they stopped training and weren't anywhere near plateauing yet. LLMs are notoriously data hungry and will take a long time to reach convergence.

Compute optimal here means the point at which it makes sense to move from a smaller to a larger model assuming that: (a) you have a fixed compute budget of FLOPs, and (b) you want to train the best model possible. The problem is that this applies only to training and assumes nothing about the cost of inference. If you actually need to deploy these trained models and support them long-term for hundreds, thousands, even millions of people to use, would you rather deploy a 13B model or a 30B model at the same level of quality, even if the 13B model would be more costly to train?

There is going to be a point at which these models plateau and further improvement will not be possible without moving to a larger model, but Llama doesn't get there quite yet.

Relevant: https://twitter.com/abacaj/status/1647999551964323844

This tweet is misunderstanding the papers.

Smaller % of training data doesn't necessarily mean lower quality.

I agree with this as well. Code has been absolutely anemic outside of GPT-3/4. One trick they used was to train it on code first and then also use a lot more code than we see in Llama even.

Same here. If you believe the following research (which I do), the ability to perform complex reasoning is likely to be from training on code:

https://yaofu.notion.site/How-does-GPT-Obtain-its-Ability-Tr...

I think it's essential to increase the quantity of code tokens.

No idea!

I wonder how hard it would be to fine-tune something built on RedPajama on further code examples to improve performance there.

Reply on news.ycombinator.com